© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68992
    Prev
    Next
    INDEX
    Explanations

    forbidden fruit and blog

    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_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
    垍
    -3.09
     hasard
    -2.92
     couteau
    -2.86
     doigt
    -2.78
     monstre
    -2.72
     crede
    -2.69
    geſ
    -2.67
     pilares
    -2.66
    簠
    -2.64
     ennemi
    -2.63
    POSITIVE LOGITS
     That
    3.39
    .
    3.31
     Notably
    3.19
     Carefully
    3.05
     If
    2.97
     Recently
    2.94
     Nonetheless
    2.84
     Roughly
    2.83
     Interestingly
    2.81
     Some
    2.78
    Activations Density 0.002%

    No Known Activations