© 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. 55346
    Prev
    Next
    INDEX
    Explanations

    local descriptions or components

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

    potential benefits, variations, or tax collection

    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
     WELL
    0.45
     Wall
    0.43
     I
    0.42
     dB
    0.42
     있는데요
    0.42
     Bundestag
    0.42
     wealthy
    0.41
     smoker
    0.41
     Cigar
    0.41
    ongyang
    0.40
    POSITIVE LOGITS
    㩴
    0.46
     கொ
    0.46
     κο
    0.45
    лі
    0.44
    мой
    0.44
    立つ
    0.43
    วิ่ง
    0.43
     ব্যাট
    0.42
    決して
    0.42
    сла
    0.42
    Activations Density 0.000%

    No Known Activations