© 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. 10-GEMMASCOPE-RES-131K
    7. 128818
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
     menant
    -1.74
     dieu
    -1.69
    magine
    -1.69
     peruan
    -1.68
     บาท
    -1.65
     rése
    -1.64
    phalt
    -1.64
     peines
    -1.63
     Octobre
    -1.63
    lieving
    -1.63
    POSITIVE LOGITS
     ultimately
    1.63
     Also
    1.63
     clearly
    1.63
     subsequently
    1.59
     then
    1.58
    </blockquote>
    1.58
     initially
    1.58
     decided
    1.57
     potentially
    1.57
    </h1>
    1.55
    Activations Density 0.022%

    No Known Activations