© 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. 36011
    Prev
    Next
    INDEX
    Explanations

    prevent seizure

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

    defining concepts or specific qualifiers

    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
    ད་
    0.46
    鉅
    0.43
    nú
    0.42
     améric
    0.42
    يرا
    0.42
     Flücht
    0.42
     thú
    0.41
    ᆯ
    0.41
    jx
    0.40
    zé
    0.40
    POSITIVE LOGITS
    шлай
    0.47
    গ্রহায়ণ
    0.45
    轳
    0.44
     setiap
    0.41
    ensin
    0.41
    的神
    0.41
     성능
    0.41
     শাসনের
    0.40
     तहत
    0.40
     Parameter
    0.40
    Activations Density 0.000%

    No Known Activations