© 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. 62164
    Prev
    Next
    INDEX
    Explanations

    successive action

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

    code documentation

    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
     chargé
    0.54
    রেক
    0.50
    Мы
    0.49
     contient
    0.48
    蘋
    0.48
    बैक
    0.48
    Ờ
    0.48
    もう
    0.47
    affichage
    0.47
     ovu
    0.47
    POSITIVE LOGITS
    for
    0.43
    </h5>
    0.41
    ucceed
    0.41
    0.41
    </h6>
    0.40
    List
    0.40
    zenia
    0.40
    Directed
    0.39
     Destinations
    0.38
    ientes
    0.38
    Activations Density 0.000%

    No Known Activations