© 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. 190104
    Prev
    Next
    INDEX
    Explanations

    function focus optimized appointment rates application

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

    settings, version, side

    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
    არ
    0.52
    ो
    0.50
    ம்பி
    0.44
    ⏱
    0.44
    ôté
    0.43
    现实
    0.43
    ✝
    0.43
    浑
    0.42
    人类
    0.42
     स्टूडियो
    0.41
    POSITIVE LOGITS
     egyik
    0.49
     http
    0.47
     বললাম
    0.46
     one
    0.45
     at
    0.44
     HTTP
    0.44
     briefs
    0.43
    http
    0.42
     on
    0.41
     একজনকে
    0.41
    Activations Density 0.003%

    No Known Activations