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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10983
    Prev
    Next
    INDEX
    Explanations

    HTML structure tags

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

    The neuron activates on standalone numeric tokens (e.g. class names or other code tokens that are purely numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     biela
    -1.62
    providedIn
    -1.48
    corrhi
    -1.45
     chère
    -1.42
     bicicletas
    -1.41
     its
    -1.41
     évé
    -1.39
     lotes
    -1.39
     réus
    -1.36
    tentu
    -1.36
    POSITIVE LOGITS
    o
    1.48
    1.39
    op
    1.33
    这类
    1.31
     afore
    1.28
    などを
    1.23
    O
    1.23
     heridos
    1.20
    で
    1.20
    fer
    1.19
    Activations Density 0.001%
    No Known Activations