© 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. 74049
    Prev
    Next
    INDEX
    Explanations

    hand towel

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

    Static, DNS, capacitor, vest

    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
    ท
    0.58
     a
    0.52
     emberek
    0.50
     esclare
    0.49
     larga
    0.49
     angry
    0.46
     aclarar
    0.46
     nach
    0.46
     otro
    0.46
     वड
    0.46
    POSITIVE LOGITS
     ಪ್ರಯೋಜನ
    0.48
    leaning
    0.47
     ಭೂ
    0.46
     ವರ್ಷ
    0.46
     //-->
    0.46
    јединачна
    0.45
    0.45
     ಪಡೆಯ
    0.45
     Prospective
    0.45
     అవకాశ
    0.44
    Activations Density 0.000%

    No Known Activations