© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51942
    Prev
    Next
    INDEX
    Explanations

    accumulated charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.57
     outward
    0.48
    -
    0.47
    }{
    0.47
    /
    0.47
    ello
    0.46
    op
    0.46
    natural
    0.45
    //
    0.45
    ismo
    0.45
    POSITIVE LOGITS
     PUBLICATIONS
    0.57
    琹
    0.47
     czter
    0.46
     研究
    0.46
    لمانيا
    0.45
    geschoss
    0.45
     Golub
    0.44
     jurisdict
    0.44
    季度
    0.44
    czeniu
    0.44
    Activations Density 0.002%

    No Known Activations