© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217745
    Prev
    Next
    INDEX
    Explanations

    Contest Winners

    np_acts-logits-general · gemini-2.5-flash-lite

    standardized purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝟬
    0.52
    prehensive
    0.49
    hingga
    0.48
    𝓭
    0.48
    Aly
    0.46
    🧊
    0.46
    लं
    0.45
    Don
    0.45
     unleashing
    0.44
    {"
    0.44
    POSITIVE LOGITS
     TB
    0.47
     maf
    0.45
     kvar
    0.45
     mils
    0.45
     cops
    0.44
     tuy
    0.44
    вость
    0.44
     geist
    0.44
     mãos
    0.43
     ihr
    0.43
    Activations Density 0.000%

    No Known Activations