© 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. 92282
    Prev
    Next
    INDEX
    Explanations

    everyone deserves respect

    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
    \</
    0.46
     doctrinal
    0.43
     나누
    0.42
    perity
    0.42
     дина
    0.42
    ussian
    0.41
    nosti
    0.41
     ({\
    0.41
     農
    0.41
    agation
    0.41
    POSITIVE LOGITS
    巅峰
    0.48
     Walmart
    0.46
     Chess
    0.44
    啻
    0.44
     Peak
    0.43
    pless
    0.42
     المباراة
    0.42
     Ster
    0.42
    விட்ட
    0.42
     Blut
    0.42
    Activations Density 0.004%

    No Known Activations