© 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. 128715
    Prev
    Next
    INDEX
    Explanations

    seldom housebroke, laughs last

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

    historical fiction

    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
    football
    0.55
    ما
    0.50
    igrants
    0.50
    鈈
    0.50
     아닌
    0.49
    kates
    0.47
    amal
    0.47
    نمية
    0.46
    観光
    0.46
    تقرير
    0.46
    POSITIVE LOGITS
     efectos
    0.49
     especializada
    0.47
     Shimizu
    0.47
     imitate
    0.45
     postice
    0.45
    Ｚ
    0.45
     portes
    0.44
     caja
    0.43
     experto
    0.43
     Exper
    0.43
    Activations Density 0.000%

    No Known Activations