© 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. 187494
    Prev
    Next
    INDEX
    Explanations

    Copyright infringement

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

    fund performance

    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
     invasions
    0.55
     invaded
    0.49
    ૧
    0.47
    resos
    0.47
     fragen
    0.46
     ocasiones
    0.45
    regen
    0.45
    ాత్ర
    0.44
     threaten
    0.44
    トラブル
    0.44
    POSITIVE LOGITS
    AR
    0.53
     Physiology
    0.47
     Abroad
    0.47
    e
    0.47
    টস
    0.47
    U
    0.46
     Audi
    0.44
     href
    0.43
     Fence
    0.43
    पणे
    0.43
    Activations Density 0.001%

    No Known Activations