© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73659
    Prev
    Next
    INDEX
    Explanations

    representations of algebras

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specifically activates on occurrences of the term “representation” (and its close variants in mathematical contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical terminology and contexts related to abstract algebra and representation theory, especially in mathematical abstracts and discussions.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    mathematical or technical terms related to representation theory and algebraic structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缡
    -1.48
     LIABLE
    -1.46
     assister
    -1.43
     吗
    -1.40
     zune
    -1.34
     beant
    -1.32
    -1.28
     nhưng
    -1.27
     δεν
    -1.27
     INDEP
    -1.24
    POSITIVE LOGITS
     of
    1.58
     gerai
    1.44
     in
    1.35
    中等
    1.26
     uitgebre
    1.25
     todėl
    1.23
     She
    1.22
     Organizador
    1.22
     Ön
    1.21
    LPS
    1.18
    Activations Density 0.023%

    No Known Activations