© 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. 219431
    Prev
    Next
    INDEX
    Explanations

    bearing performance currently

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

    theoretical frameworks, Facebook bundle, won round

    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
    醝
    0.46
     본격
    0.44
     제목
    0.43
     자동으로
    0.43
    јединачна
    0.42
     আরে
    0.42
    صرية
    0.41
     진짜
    0.41
     '<
    0.40
    杀死
    0.40
    POSITIVE LOGITS
     Mindanao
    0.48
     selama
    0.47
     manteniendo
    0.46
     submersible
    0.46
     stesse
    0.46
     lão
    0.45
     mantienen
    0.45
    scaron
    0.45
     mantenerse
    0.45
     mantuvo
    0.44
    Activations Density 0.002%

    No Known Activations