© 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. 126479
    Prev
    Next
    INDEX
    Explanations

    for people, thing, upholstery

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

    explaining why or what

    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
     গ্রন্থের
    0.50
    wells
    0.48
     ও
    0.46
     व
    0.46
     sugiere
    0.46
     suss
    0.45
    லத்தில்
    0.44
    ि
    0.44
    veld
    0.43
    ীকে
    0.43
    POSITIVE LOGITS
    쳤
    0.46
    ны
    0.46
    omás
    0.46
    requency
    0.46
    人
    0.45
    utom
    0.44
    受
    0.43
     Scor
    0.43
    網絡
    0.42
    ント
    0.42
    Activations Density 0.002%

    No Known Activations