© 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. 7882
    Prev
    Next
    INDEX
    Explanations

    Author followed by names

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

    This neuron detects boilerplate license/header metadata (e.g. Copyright, Author, License, SPDX, URLs) in source‐code comment blocks.

    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
     how
    -1.82
     sabias
    -1.71
     you
    -1.69
     your
    -1.68
     such
    -1.67
     verschillende
    -1.67
     its
    -1.66
     today
    -1.63
    
    -1.61
     использова
    -1.49
    POSITIVE LOGITS
    providedIn
    1.73
    ;
    1.63
    Those
    1.63
    although
    1.52
    :
    1.48
    That
    1.45
    кому
    1.44
    готовки
    1.44
    ."
    1.41
    Unlike
    1.41
    Activations Density 0.313%

    No Known Activations