© 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. 222042
    Prev
    Next
    INDEX
    Explanations

    can, could, visit

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

    variation, differences, specific examples

    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
    首先
    0.50
    ärsk
    0.49
    樑
    0.46
    雹
    0.46
    Length
    0.46
    Size
    0.45
    島
    0.44
    手法
    0.43
     Франции
    0.43
     Geheim
    0.43
    POSITIVE LOGITS
     reluct
    0.53
    밋
    0.52
     pollo
    0.51
     intest
    0.48
    찹
    0.48
    ورك
    0.48
    인더
    0.47
    ابی
    0.46
     arti
    0.44
     aes
    0.44
    Activations Density 0.000%

    No Known Activations