© 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. 174130
    Prev
    Next
    INDEX
    Explanations

    sometimes wondering why

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

    realized understanding capabilities

    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
    물
    0.53
    물이
    0.52
    ज
    0.47
    まとめ
    0.45
    붙
    0.45
     retreats
    0.45
    징
    0.45
    வுகளை
    0.44
    우
    0.44
    ती
    0.44
    POSITIVE LOGITS
    ült
    0.49
    ilers
    0.45
    gerät
    0.45
     Gött
    0.44
    ruh
    0.44
     vint
    0.44
    nera
    0.43
     eigentlich
    0.43
    geschichte
    0.43
    flächen
    0.43
    Activations Density 0.001%

    No Known Activations