© 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. 179016
    Prev
    Next
    INDEX
    Explanations

    correspondence and letters

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

    already trademarked or used

    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
     mandates
    0.52
    нова
    0.50
    formulas
    0.50
    افت
    0.49
    る
    0.49
    ⎪
    0.49
    ké
    0.49
    мати
    0.48
    Пе
    0.48
    ে
    0.47
    POSITIVE LOGITS
     Joy
    0.46
     Forest
    0.46
     Cigar
    0.46
     kicker
    0.45
     Troops
    0.45
    urbed
    0.45
     গার্ম
    0.45
     Pawan
    0.45
     Soldaten
    0.44
     Thank
    0.44
    Activations Density 0.001%

    No Known Activations