© 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. 237532
    Prev
    Next
    INDEX
    Explanations

    essay topics

    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
    िसोदिया
    0.53
    掟
    0.50
     contributo
    0.49
    笃
    0.46
    ریب
    0.46
    రిత్ర
    0.46
    谭
    0.46
    预测
    0.45
     মন্তব্য
    0.45
    쫌
    0.45
    POSITIVE LOGITS
    simple
    0.52
    first
    0.52
    jf
    0.50
    angers
    0.49
    -
    0.48
    lasts
    0.47
    :
    0.47
    intervals
    0.46
     unforgettable
    0.46
    adap
    0.46
    Activations Density 0.002%

    No Known Activations