© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 86945
    Prev
    Next
    INDEX
    Explanations

    super, Rejection, V, Q, 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    telah
    -0.85
     punished
    -0.79
     INDIANA
    -0.78
    ADATA
    -0.77
    ソッド
    -0.76
     beside
    -0.74
     평
    -0.74
    เ
    -0.73
     редак
    -0.73
    __('
    -0.73
    POSITIVE LOGITS
    gatan
    0.82
     loom
    0.75
    forts
    0.72
    Juegos
    0.72
    gesture
    0.71
     conceive
    0.69
    Simpli
    0.68
     любит
    0.66
     Schatten
    0.66
     decline
    0.66
    Activations Density 0.003%

    No Known Activations