© 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. 85016
    Prev
    Next
    INDEX
    Explanations

    lab registry files

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

    general or basic product concepts

    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
     Display
    0.49
     완
    0.48
     opis
    0.45
     W
    0.44
     Commission
    0.44
     komplet
    0.43
     Power
    0.43
     기
    0.43
     Demon
    0.43
     Pro
    0.43
    POSITIVE LOGITS
    ahooks
    0.46
     tradeoffs
    0.46
    mixing
    0.46
    congestion
    0.44
    性を
    0.44
     یونیورسٹی
    0.43
    balancing
    0.43
     রকমের
    0.43
    problem
    0.43
    fixing
    0.43
    Activations Density 0.000%

    No Known Activations