© 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. 175973
    Prev
    Next
    INDEX
    Explanations

    these results

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

    searching for index and locations

    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
     православ
    0.54
     නමුත්
    0.53
     Vanuatu
    0.53
     aik
    0.52
     Kı
    0.47
     выборах
    0.47
    =[];
    0.46
     divulge
    0.46
     وړاندوینې
    0.46
     Antio
    0.46
    POSITIVE LOGITS
    هر
    0.56
    ح
    0.52
    우
    0.52
    وير
    0.51
    rolling
    0.49
    ஷ
    0.49
    mités
    0.49
    rę
    0.48
    rg
    0.48
    庣
    0.47
    Activations Density 0.001%

    No Known Activations