© 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. 191864
    Prev
    Next
    INDEX
    Explanations

    print zone

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

    tutorialspoint, Next Phase, Avoid vague

    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
    na
    0.57
    all
    0.55
    K
    0.54
    te
    0.51
    pr
    0.49
    urre
    0.49
    ri
    0.49
    zi
    0.49
    rs
    0.49
    on
    0.48
    POSITIVE LOGITS
    MessageType
    0.46
     industrialized
    0.44
    店舗
    0.43
     discouraged
    0.43
    форм
    0.43
    ObjData
    0.42
    плы
    0.42
     Englewood
    0.42
    👘
    0.42
     contended
    0.42
    Activations Density 0.000%

    No Known Activations