© 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. 119975
    Prev
    Next
    INDEX
    Explanations

    wide range of

    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
    dáms
    -2.16
    戆
    -2.02
    鼉
    -1.96
    起来的
    -1.95
    𖤣
    -1.90
    -1.85
    
    -1.83
    ⚣
    -1.83
     maxim
    -1.80
    <
    -1.80
    POSITIVE LOGITS
     of
    3.14
    This
    1.90
     attiv
    1.82
    </strong>
    1.80
     развитие
    1.77
    ве
    1.75
    áneas
    1.75
    These
    1.73
     .
    1.72
    </em>
    1.69
    Activations Density 0.010%
    No Known Activations