© 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. 180823
    Prev
    Next
    INDEX
    Explanations

    clarifications and warnings

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

    json structure with confidence

    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
    ulants
    0.38
    ULA
    0.37
    ملك
    0.37
    谈
    0.37
    복
    0.36
    ifel
    0.36
     זיי
    0.35
     질
    0.35
     Silber
    0.35
    目的是
    0.35
    POSITIVE LOGITS
    विता
    0.44
     attendant
    0.43
     accompanying
    0.43
     prochaine
    0.42
     clarification
    0.41
     watering
    0.41
     warnings
    0.39
     evap
    0.39
     cautions
    0.39
     clarifications
    0.39
    Activations Density 0.003%

    No Known Activations