© 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. 120346
    Prev
    Next
    INDEX
    Explanations

    multi-language identification

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

    conditional statements and follow-ups

    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
    ut
    0.60
    in
    0.57
    ↵↵
    0.50
    ro
    0.48
     ha
    0.48
    iet
    0.45
    zi
    0.45
     han
    0.45
     cuc
    0.45
     for
    0.45
    POSITIVE LOGITS
     eğer
    0.51
    眈
    0.50
     செய்தால்
    0.48
    迈
    0.47
     மிகு
    0.46
     चिह्न
    0.46
    Pokud
    0.46
    Если
    0.45
    पीड़न
    0.45
    假如
    0.45
    Activations Density 0.000%

    No Known Activations