© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 110434
    Prev
    Next
    INDEX
    Explanations

    desktop applications

    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
     with
    0.49
    ↵
    0.47
     house
    0.47
     number
    0.44
    max
    0.44
     look
    0.43
     segno
    0.43
     dessen
    0.41
    .
    0.41
     egy
    0.40
    POSITIVE LOGITS
    გრამ
    0.49
     Фурга
    0.49
     основы
    0.47
     Осно
    0.46
     учителя
    0.46
    MainActivityTest
    0.46
     Украї
    0.45
    <unused79>
    0.44
    रविवार
    0.43
    浲
    0.43
    Activations Density 0.007%

    No Known Activations