© 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. 189883
    Prev
    Next
    INDEX
    Explanations

    swear by, know as, better than, ultimately resolves

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

    rating and playing mechanics

    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
    岬
    0.49
    گران
    0.43
    皮
    0.43
    皮膚
    0.43
    ｯ
    0.42
     %).
    0.42
    Besch
    0.41
    TAK
    0.41
     śmier
    0.41
    澍
    0.41
    POSITIVE LOGITS
     parser
    0.50
     natively
    0.48
    idated
    0.48
    idation
    0.46
    on
    0.46
    $$_
    0.46
    imiz
    0.45
     rambling
    0.44
     跳转
    0.43
    ad
    0.43
    Activations Density 0.001%

    No Known Activations