© 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. 16333
    Prev
    Next
    INDEX
    Explanations

    biblical citations or numbers

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

    sometimes, high, long, among

    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
    وْ
    0.49
    राजनी
    0.47
    ॓
    0.46
     musculaire
    0.45
    ϙ
    0.44
    تاة
    0.44
    뮈
    0.44
    👫
    0.43
    ০১
    0.43
    
    0.43
    POSITIVE LOGITS
    in
    0.59
     {
    0.56
    0.49
     Int
    0.48
    t
    0.48
     beat
    0.46
     Description
    0.46
     sneak
    0.46
     Kai
    0.46
     want
    0.45
    Activations Density 0.000%

    No Known Activations