© 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. 38690
    Prev
    Next
    INDEX
    Explanations

    throwing a ball or object

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

    throwing accuracy

    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
    躏
    0.43
    ัตว์
    0.41
     geschaffen
    0.40
    chrift
    0.40
    шивания
    0.40
     esterno
    0.39
    ्यूड
    0.39
    culaire
    0.39
     области
    0.38
    Dropout
    0.38
    POSITIVE LOGITS
    apt
    0.45
    Ғ
    0.43
     famously
    0.42
    let
    0.42
    abouts
    0.41
     rarely
    0.41
    values
    0.40
     Louisiana
    0.40
    แข็ง
    0.39
    JP
    0.38
    Activations Density 0.006%

    No Known Activations