© 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. 173713
    Prev
    Next
    INDEX
    Explanations

    honour, communities, without replacement

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

    intellectual curiosity and origins

    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
     Waterford
    0.50
    ik
    0.49
     Marm
    0.48
     Rehab
    0.46
    ammak
    0.46
     Goose
    0.46
     Ball
    0.46
     N
    0.45
    s
    0.45
    iss
    0.45
    POSITIVE LOGITS
    Từ
    0.60
    ТА
    0.53
    尤
    0.50
    ConsoleText
    0.49
    Longueur
    0.49
    י
    0.49
    Ť
    0.49
    🛹
    0.49
    intă
    0.48
    뻐
    0.48
    Activations Density 0.001%

    No Known Activations