© 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. 10-GEMMASCOPE-RES-131K
    7. 111278
    Prev
    Next
    INDEX
    Explanations

    code and data delimiters

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

    opening single quotes in code strings, particularly in SQL queries and string assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron consistently fires on numeric literals (including numbers in quotes or with punctuation) in the 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_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
    があります
    -2.06
    了啊
    -1.92
     a
    -1.92
     весьма
    -1.85
    ar
    -1.80
    ↵
    -1.80
     incontr
    -1.72
    蘗
    -1.71
    s
    -1.65
     schwier
    -1.63
    POSITIVE LOGITS
     we
    2.09
    '
    1.71
    </strong>
    1.68
    、
    1.62
     sierpnia
    1.55
    rodalom
    1.54
    días
    1.53
    видно
    1.52
    enterOuterAlt
    1.52
    ,
    1.52
    Activations Density 0.030%

    No Known Activations