© 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. 29370
    Prev
    Next
    INDEX
    Explanations

    knocking the

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

    dates and events

    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
    م
    0.47
    Cats
    0.46
    ט
    0.45
    금
    0.45
    vindo
    0.43
     Cats
    0.42
     dogs
    0.42
    镞
    0.42
    kä
    0.42
    ٹ
    0.42
    POSITIVE LOGITS
    popupBackground
    0.53
    řízení
    0.50
    ᱵ
    0.49
    beis
    0.48
    снаб
    0.48
    луйста
    0.46
    гна
    0.45
     Linie
    0.45
    britann
    0.44
    гах
    0.44
    Activations Density 0.000%

    No Known Activations