© 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. 145362
    Prev
    Next
    INDEX
    Explanations

    USA data cables

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

    regular inspections

    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
    ინ
    0.51
    チ
    0.50
     Хабаров
    0.48
    一緒に
    0.47
    達到
    0.46
     кул
    0.46
    そして
    0.45
     инвести
    0.45
    ТИ
    0.45
    ઇ
    0.45
    POSITIVE LOGITS
     America
    0.48
     West
    0.47
     Camera
    0.46
     X
    0.46
     O
    0.45
     W
    0.45
     Combustion
    0.44
     George
    0.44
    jd
    0.44
     tű
    0.44
    Activations Density 0.000%

    No Known Activations