© 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. 46481
    Prev
    Next
    INDEX
    Explanations

    available. basically do. primarily do. impact of. place an

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

    "though penile", "not a", "not fixed", "not a video"

    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
    Meal
    0.42
     T
    0.42
    ხვა
    0.41
     pratiquer
    0.41
    FL
    0.41
     khổ
    0.41
    Loan
    0.41
     borrower
    0.40
     primal
    0.40
    ریر
    0.40
    POSITIVE LOGITS
    in
    0.53
    to
    0.47
    l
    0.46
    albeit
    0.46
    ar
    0.46
    laughs
    0.45
    ं
    0.45
     unsurprisingly
    0.45
    桻
    0.44
    as
    0.44
    Activations Density 0.000%

    No Known Activations