© 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. 130737
    Prev
    Next
    INDEX
    Explanations

    end of line/comment/code

    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
    蟶
    -1.98
    簠
    -1.98
    鉭
    -1.88
    癭
    -1.86
    튿
    -1.85
     erwähnt
    -1.80
     entraîner
    -1.80
    ܆
    -1.77
    
    -1.77
    often
    -1.76
    POSITIVE LOGITS
     of
    3.41
     with
    2.00
     in
    1.79
    There
    1.77
    Like
    1.70
     only
    1.70
     could
    1.69
    Only
    1.64
    ,
    1.63
    This
    1.63
    Activations Density 0.005%

    No Known Activations