© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25270
    Prev
    Next
    INDEX
    Explanations

    code imports and definitions

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

    The neuron fires on isolated identifier tokens that serve as field or property names (the keys) in configuration or metadata assignments.

    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
     tertawa
    -1.55
    БЕ
    -1.54
    движи
    -1.52
     hunde
    -1.49
    ЦЕ
    -1.47
     Bretaña
    -1.44
    𓄹
    -1.42
    鶺
    -1.39
     対策
    -1.38
     menyen
    -1.38
    POSITIVE LOGITS
    Y
    1.82
     was
    1.59
    L
    1.54
    ’
    1.41
    //
    1.39
    t
    1.38
    P
    1.38
    e
    1.34
    g
    1.34
    '
    1.32
    Activations Density 0.008%

    No Known Activations