© 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. 128041
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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
     Erkrank
    -0.82
    mètre
    -0.74
    حسب
    -0.71
     xadrez
    -0.71
     дуже
    -0.70
    <0xD5>
    -0.70
     Gegenwart
    -0.70
    ְר
    -0.70
    gut
    -0.69
     aniversário
    -0.69
    POSITIVE LOGITS
     Urbana
    0.88
    igraph
    0.85
    اج
    0.85
    ウチ
    0.83
    ⅖
    0.82
    samp
    0.81
    कड
    0.80
    обще
    0.80
    ifndef
    0.80
    Pg
    0.79
    Activations Density 0.025%

    No Known Activations