© 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. 157973
    Prev
    Next
    INDEX
    Explanations

    closing parentheses

    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
    mast
    0.54
    áme
    0.49
    acija
    0.49
    oud
    0.46
    ),"
    0.46
    修建
    0.44
    :"
    0.43
     primit
    0.42
    avent
    0.42
    ap
    0.42
    POSITIVE LOGITS
     ເ
    0.50
    лябин
    0.45
     Refer
    0.43
     इससे
    0.42
    swering
    0.41
    णू
    0.40
    referred
    0.40
     coment
    0.40
    BLOCK
    0.40
     следующие
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.