© 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. 34-GEMMASCOPE-RES-131K
    7. 3086
    Prev
    Next
    INDEX
    Explanations

    name = assignment

    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
    ллю
    -0.91
     type
    -0.84
    子さん
    -0.80
     or
    -0.80
     why
    -0.77
     Arxivat
    -0.77
    antd
    -0.76
    Un
    -0.75
    All
    -0.75
     all
    -0.73
    POSITIVE LOGITS
    イト
    0.93
    ならでは
    0.91
     dismant
    0.90
    DOU
    0.87
    тового
    0.86
     SUCH
    0.85
     Trouvez
    0.84
    tected
    0.84
     Cada
    0.83
    σκ
    0.83
    Activations Density 0.002%

    No Known Activations