© 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. 8258
    Prev
    Next
    INDEX
    Explanations

    common prepositions and conjunctions

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

    The neuron is especially sensitive to long, domain-specific technical nouns and jargon (e.g. patentability, prenatal/fetal, data, Dubai in a technical context).

    oai_token-act-pair · o4-miniTriggered 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
     or
    -1.52
     are
    -1.41
    -1.29
    Как
    -1.20
    然而
    -1.18
    форма
    -1.17
    -1.16
     etc
    -1.12
    Seperti
    -1.12
    DECISION
    -1.11
    POSITIVE LOGITS
     festgestellt
    1.45
     jednej
    1.44
    みを
    1.36
     okno
    1.27
     klasa
    1.27
     Estamos
    1.25
     leuke
    1.23
     gemessen
    1.22
     rústica
    1.21
     takimi
    1.21
    Activations Density 0.265%

    No Known Activations