© 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. 22-GEMMASCOPE-RES-131K
    7. 25837
    Prev
    Next
    INDEX
    Explanations

    United States

    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_22/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
     if
    -0.84
    ittäin
    -0.81
    Ӏ
    -0.81
     ged
    -0.80
    leggio
    -0.80
    ESSOR
    -0.77
    的角色
    -0.77
    祥
    -0.77
     Осо
    -0.75
    康
    -0.75
    POSITIVE LOGITS
    uerst
    0.94
     carinho
    0.91
    werkt
    0.89
    even
    0.85
    还挺
    0.84
    costal
    0.84
     trova
    0.84
    申し上げます
    0.83
    cte
    0.82
    gamesh
    0.81
    Activations Density 0.002%

    No Known Activations