© 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. 107721
    Prev
    Next
    INDEX
    Explanations

    options, series, hospital, week, alternatives

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

    categories and examples

    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
    tter
    0.48
     Unter
    0.45
     Bet
    0.45
    ucing
    0.45
    typing
    0.45
     ß
    0.44
     Grö
    0.44
    piele
    0.44
    颼
    0.44
    vis
    0.43
    POSITIVE LOGITS
    舫
    0.55
    घु
    0.51
    ্যাপ
    0.49
    চাল
    0.49
    랠
    0.49
     dựng
    0.48
    ढ़ा
    0.48
    গ্
    0.47
    কর্
    0.46
    இந்நிலையில்
    0.46
    Activations Density 0.001%

    No Known Activations