© 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. 59762
    Prev
    Next
    INDEX
    Explanations

    14-month registration

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

    less expensive, 5-minute window, block of memory

    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
    杭州
    0.48
    RG
    0.45
    局
    0.45
    針對
    0.45
     teoria
    0.44
    Halo
    0.44
     Reign
    0.44
    Writing
    0.44
    Investing
    0.43
    規範
    0.43
    POSITIVE LOGITS
     neum
    0.51
     psychology
    0.48
     elucidation
    0.48
    neum
    0.48
     memperoleh
    0.45
     sáb
    0.44
    های
    0.44
    传来
    0.44
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.44
    skie
    0.44
    Activations Density 0.000%

    No Known Activations