© 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. 15217
    Prev
    Next
    INDEX
    Explanations

    talk followed by common suffixes or 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_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
     \
    -2.97
     to
    -2.14
     apparent
    -2.13
     —
    -2.00
     
    -1.99
     –
    -1.95
     argument
    -1.93
     "",
    -1.91
     approaching
    -1.87
    ↵
    -1.86
    POSITIVE LOGITS
     插画
    2.58
    acterísticas
    2.52
    你的
    2.44
    𖣘
    2.41
    Ꮻ
    2.36
    镔
    2.33
     古风
    2.31
    寕
    2.31
    洇
    2.31
     ответил
    2.30
    Activations Density 0.011%

    No Known Activations