© 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. 7388
    Prev
    Next
    INDEX
    Explanations

    and followed by words

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

    and complete, didn, give, warm, tried

    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
     Nonlinear
    0.25
     constitute
    0.25
    ઃ
    0.24
    Accordingly
    0.24
    ‌,
    0.24
    <0xBF>
    0.24
    ـ
    0.23
    を超
    0.23
    <0xBD>
    0.23
    ؛
    0.23
    POSITIVE LOGITS
     soooo
    0.33
     якщо
    0.32
     didn
    0.31
     sooo
    0.31
     whatnot
    0.31
     nagyon
    0.30
     there
    0.30
     מאוד
    0.30
     voila
    0.30
     we
    0.29
    Activations Density 1.326%

    No Known Activations