© 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. 45556
    Prev
    Next
    INDEX
    Explanations

    search, entry, revolution, trading

    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
    Inspector
    0.49
    /////////
    0.49
    Preview
    0.48
    סה
    0.48
    ΟΥ
    0.47
    /////////////
    0.47
    Đặt
    0.47
    代表
    0.46
    U
    0.46
    Things
    0.46
    POSITIVE LOGITS
     livelihood
    0.50
     SED
    0.48
     Arroyo
    0.47
     impetus
    0.47
     leeway
    0.47
    gruppen
    0.46
     EDP
    0.46
     unjust
    0.45
     નિર્ણય
    0.45
     livelihoods
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.