© 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. 10847
    Prev
    Next
    INDEX
    Explanations

    code and comments

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

    underscores in code or technical identifiers.

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

    The neuron fires on underscore characters in programming identifiers.

    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
    。"
    -2.09
    dáms
    -2.05
    '
    -1.96
     estampado
    -1.73
     elástico
    -1.69
     bordado
    -1.67
     delicada
    -1.66
     silencioso
    -1.64
     chaleco
    -1.64
     elástica
    -1.64
    POSITIVE LOGITS
     they
    2.05
     to
    1.93
    雯
    1.61
    )();
    1.57
     ところ
    1.56
    𝗿
    1.56
     inadequacy
    1.52
     wrze
    1.51
    ሎ
    1.46
    涐
    1.46
    Activations Density 0.000%

    No Known Activations