© 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. 173216
    Prev
    Next
    INDEX
    Explanations

    principles, Inc, ERP, patient, batteries

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

    car properties

    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
    t
    0.48
     Sector
    0.47
    الش
    0.46
    ˂
    0.46
    lik
    0.45
    ꯠ
    0.45
     Coal
    0.45
    ایت
    0.45
    惕
    0.45
    sector
    0.44
    POSITIVE LOGITS
     און
    0.54
    スー
    0.49
    FirstResponder
    0.48
     snapped
    0.46
     ಕೆಲಸ
    0.45
     עם
    0.45
     degraded
    0.45
    Denied
    0.44
    짬
    0.43
    灲
    0.43
    Activations Density 0.001%

    No Known Activations