© 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. 158377
    Prev
    Next
    INDEX
    Explanations

    mocking laughter

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

    sexual restrictions and community norms

    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
    naie
    0.45
    니다
    0.41
    ↵
    0.41
    ),”
    0.40
     kehadiran
    0.40
     bungalows
    0.40
    --*/
    0.40
     resa
    0.40
    ُونَ
    0.39
    ngthen
    0.39
    POSITIVE LOGITS
    jumping
    0.64
     أو
    0.55
     পত্রিকায়
    0.54
     Nhiều
    0.54
    вле
    0.52
     ปี
    0.52
    redirectTo
    0.52
     أبريل
    0.52
     năm
    0.50
     ແ
    0.50
    Activations Density 0.000%

    No Known Activations