© 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. 190218
    Prev
    Next
    INDEX
    Explanations

    Calendar dates and events

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

    prefix for lists or enumerations

    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
    fire
    0.47
     wohn
    0.46
    fiction
    0.45
     reinforcement
    0.44
     luminance
    0.43
    arbe
    0.43
    <start_of_image>
    0.42
    nicht
    0.42
     cytotoxic
    0.42
    зне
    0.42
    POSITIVE LOGITS
     ساده
    0.54
    পা
    0.54
    SQLException
    0.50
    Cantidad
    0.49
     تھا
    0.48
     勺
    0.48
    şağı
    0.48
    )，
    0.47
    ..)
    0.47
     ہُ
    0.47
    Activations Density 0.000%

    No Known Activations