© 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. 194797
    Prev
    Next
    INDEX
    Explanations

    personal home, would force, strategic sales

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

    special sections for lists

    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
    :"",
    0.55
    ensureEqual
    0.54
     واحدة
    0.54
    salaryfrom
    0.52
    ה
    0.51
    דיו
    0.51
    aeskeygenassist
    0.50
     ಕಾಂಗ್ರೆ
    0.49
     ঘুরে
    0.49
    ശ്വാ
    0.49
    POSITIVE LOGITS
    (
    0.67
     metering
    0.57
    -
    0.55
     to
    0.54
     by
    0.52
     meter
    0.52
     solidification
    0.51
     forming
    0.50
     once
    0.49
     conversion
    0.49
    Activations Density 0.000%

    No Known Activations