© 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. 34-GEMMASCOPE-RES-131K
    7. 49916
    Prev
    Next
    INDEX
    Explanations

    code syntax and types

    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
    
    -0.98
     fenders
    -0.95
    LEBR
    -0.93
    GALL
    -0.92
    ).....
    -0.88
     TILL
    -0.88
    颔
    -0.88
     creado
    -0.88
    liac
    -0.87
    iog
    -0.87
    POSITIVE LOGITS
    volatile
    0.90
    骁
    0.89
     very
    0.88
     as
    0.84
     ((
    0.84
     (
    0.84
     four
    0.82
    )});
    0.82
     JUST
    0.81
     Certainly
    0.81
    Activations Density 0.001%

    No Known Activations