© 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. 22-GEMMASCOPE-RES-131K
    7. 33163
    Prev
    Next
    INDEX
    Explanations

    code and non-English words

    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_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
     again
    -1.02
    同様に
    -0.92
    morphic
    -0.92
    namental
    -0.90
     XXXII
    -0.89
    again
    -0.88
    ened
    -0.88
    e
    -0.86
    fest
    -0.86
     zune
    -0.86
    POSITIVE LOGITS
     ventilador
    1.05
    Đây
    1.02
    ЛИ
    0.96
     derni
    0.93
    ὗ
    0.92
     ktoré
    0.91
     Veuillez
    0.91
     tričko
    0.91
     когато
    0.90
     Scalars
    0.90
    Activations Density 0.010%

    No Known Activations