© 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. 11621
    Prev
    Next
    INDEX
    Explanations

    local files or program scope

    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
    axter
    0.40
     liqueur
    0.39
    𝘼
    0.39
    វិញ
    0.38
    sister
    0.38
     сестра
    0.38
     Schwester
    0.37
    INH
    0.36
    ኮ
    0.36
     sister
    0.36
    POSITIVE LOGITS
     Local
    0.62
     local
    0.59
     স্থানীয়
    0.58
    局部
    0.57
    Local
    0.56
    local
    0.54
     localize
    0.53
     LOCAL
    0.52
     localidades
    0.52
    本地
    0.52
    Activations Density 0.001%

    No Known Activations