© 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. 198483
    Prev
    Next
    INDEX
    Explanations

    purchase following may

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

    description or definition

    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
    -
    0.54
    <0x80>
    0.46
    ained
    0.45
    uke
    0.44
    вай
    0.44
    aid
    0.44
    group
    0.43
    rive
    0.43
    да
    0.43
    йма
    0.43
    POSITIVE LOGITS
    ศาส
    0.48
    厂
    0.47
     uzyska
    0.47
     ismi
    0.46
     egensk
    0.46
     sebebi
    0.46
     Роди
    0.45
     kullanımı
    0.45
    恽
    0.44
     utan
    0.43
    Activations Density 0.000%

    No Known Activations