© 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. 156541
    Prev
    Next
    INDEX
    Explanations

    ticket websites and marketplaces

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

    natural production

    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
     чуде
    0.52
    əsi
    0.51
    !।
    0.50
     книге
    0.50
     свого
    0.49
     ይሰ
    0.49
    <unused333>
    0.49
     CCSDT
    0.48
    雱
    0.48
     связано
    0.47
    POSITIVE LOGITS
    </h3>
    0.54
    class
    0.52
    operator
    0.52
    ↵
    0.48
    operators
    0.48
    uct
    0.48
    to
    0.47
    secret
    0.45
     Operators
    0.45
    </h2>
    0.44
    Activations Density 0.000%

    No Known Activations