© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68181
    Prev
    Next
    INDEX
    Explanations

    go package words

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

    The neuron primarily detects occurrences of line‐comment delimiters (the “//” comment marker) in code.

    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
     miniaturka
    -1.56
     plafon
    -1.48
     célè
    -1.48
     チラ
    -1.46
     méda
    -1.44
     vermel
    -1.42
     coreano
    -1.41
     disponibilités
    -1.39
     Tratado
    -1.39
    蚰
    -1.38
    POSITIVE LOGITS
     is
    2.05
     to
    1.83
     B
    1.65
     has
    1.63
     C
    1.63
     W
    1.62
     L
    1.60
     M
    1.59
     R
    1.59
     an
    1.58
    Activations Density 0.009%

    No Known Activations