© 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. 69215
    Prev
    Next
    INDEX
    Explanations

    harsh looking, waiting for, training in

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

    percentages, numerical details, median

    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
     fanatic
    0.57
     forbidding
    0.49
     fined
    0.49
    rene
    0.47
     nib
    0.47
    V
    0.47
     rug
    0.47
     forbid
    0.46
     seek
    0.46
     fan
    0.45
    POSITIVE LOGITS
    lmp
    0.49
    ード
    0.47
    كيت
    0.46
    frequencies
    0.45
    ┉
    0.44
     mangiare
    0.44
    播
    0.44
    ارات
    0.43
    evento
    0.43
    ق
    0.43
    Activations Density 0.000%

    No Known Activations