© 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. 137163
    Prev
    Next
    INDEX
    Explanations

    see below

    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
     H
    0.60
     Binary
    0.59
     g
    0.57
     T
    0.56
     M
    0.56
     tog
    0.54
     Latinoamérica
    0.54
     UA
    0.53
     PvP
    0.53
     sashimi
    0.53
    POSITIVE LOGITS
    remain
    0.53
    replaceable
    0.52
    unknown
    0.51
    inov
    0.50
    em
    0.48
    expired
    0.48
    ad
    0.47
    ຈະ
    0.47
    be
    0.46
    애
    0.46
    Activations Density 0.000%

    No Known Activations