© 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. 48640
    Prev
    Next
    INDEX
    Explanations

    foreign language

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

    tweet formatting

    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
    http
    0.54
     http
    0.49
    setFixedHeight
    0.46
    Đây
    0.45
     这是
    0.44
     ২০১৪
    0.42
    这是一
    0.42
    ⁧
    0.42
     aka
    0.41
    took
    0.41
    POSITIVE LOGITS
     insanların
    0.46
     tremend
    0.44
     lern
    0.43
     ferv
    0.43
     komfort
    0.43
    "+"|".
    0.42
     Ausdruck
    0.42
    виться
    0.41
     Komponenten
    0.41
     अन्याय
    0.41
    Activations Density 0.007%

    No Known Activations