© 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. 33431
    Prev
    Next
    INDEX
    Explanations

    existing methods or systems

    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
    <bos>
    -0.91
    贝
    -0.85
    吅
    -0.83
     puede
    -0.82
    BIÉN
    -0.79
    хни
    -0.78
    看了
    -0.77
    ઔ
    -0.77
     metter
    -0.76
     настрой
    -0.76
    POSITIVE LOGITS
     there
    0.89
     where
    0.84
     Normally
    0.78
     from
    0.77
    上官
    0.74
    ;
    0.73
    家が
    0.73
    ございました
    0.71
     къде
    0.71
     describes
    0.71
    Activations Density 0.231%

    No Known Activations