© 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. 242830
    Prev
    Next
    INDEX
    Explanations

    reduction, cutting, or temperature measurements

    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
    。
    0.52
    ।
    0.50
    注重
    0.47
    ]=
    0.41
    Departure
    0.40
     Departure
    0.40
    一
    0.40
    Construction
    0.39
    ;.
    0.39
    чити
    0.39
    POSITIVE LOGITS
    𒈪
    0.52
     disminuir
    0.52
     aplatis
    0.52
     reducir
    0.49
     demarc
    0.49
     mutil
    0.49
     température
    0.48
     tatou
    0.48
     カット
    0.48
     マスター
    0.48
    Activations Density 0.000%

    No Known Activations