© 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. 38096
    Prev
    Next
    INDEX
    Explanations

    property owned

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

    breakdown of aspects

    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
    on
    0.49
     using
    0.49
    addListener
    0.49
    plectic
    0.48
    acket
    0.47
     add
    0.44
    F
    0.44
     menggunakan
    0.44
    ヶ
    0.44
    xl
    0.43
    POSITIVE LOGITS
     Эль
    0.47
     불구하고
    0.46
    เฉพาะ
    0.44
     অনেকটা
    0.44
     Викто
    0.41
     скульп
    0.41
     добре
    0.41
     Rooney
    0.41
     первых
    0.41
     середине
    0.40
    Activations Density 0.000%

    No Known Activations