© 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. 72333
    Prev
    Next
    INDEX
    Explanations

    action/creation verbs

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

    maintain, protect, create

    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
    리와
    0.47
     в
    0.46
     Pakistani
    0.42
    ものは
    0.42
     mike
    0.40
    /
    0.40
     i
    0.39
     Political
    0.39
    титься
    0.39
     ڈھاکہ
    0.39
    POSITIVE LOGITS
     创建
    0.49
     Созда
    0.48
    CreateWall
    0.48
     该
    0.47
    BtnPanel
    0.47
     préparer
    0.46
     garantir
    0.46
    ীব্র
    0.46
    Reusable
    0.45
     إنشاء
    0.45
    Activations Density 0.001%

    No Known Activations