© 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. 12687
    Prev
    Next
    INDEX
    Explanations

    true, false, or specific values

    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
    𝙚
    0.54
     показыва
    0.53
     बिलियन
    0.52
    𝙞
    0.51
    ㈣
    0.51
     রাসেল
    0.49
     fileprivate
    0.47
     שני
    0.47
    ಪಟ್ಟ
    0.46
     మూ
    0.46
    POSITIVE LOGITS
    く
    0.55
    ž
    0.52
    女子
    0.48
    たら
    0.48
    بط
    0.47
    F
    0.47
    گ
    0.45
    配
    0.45
    그
    0.45
    čk
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.