© 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. 36114
    Prev
    Next
    INDEX
    Explanations

    corks, child, sail, from India

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

    Stanley Park

    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
    न
    0.63
    ন
    0.57
    ad
    0.56
    ża
    0.51
    ése
    0.51
     Rens
    0.51
    co
    0.50
    bz
    0.49
    nés
    0.49
     Pérez
    0.49
    POSITIVE LOGITS
    待遇
    0.48
    片
    0.47
    錨
    0.47
    星
    0.46
    肌
    0.46
    實現
    0.45
    ర్వాత
    0.45
    れていた
    0.44
    季節
    0.44
    在
    0.43
    Activations Density 0.000%

    No Known Activations