© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3451
    Prev
    Next
    INDEX
    Explanations

    language detection

    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_40_width_65k_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
     exer
    0.34
    '})
    0.33
     tell
    0.31
     equival
    0.31
     &'
    0.31
    様な
    0.29
     extol
    0.29
    ंबल
    0.29
    ,'"
    0.29
    Tell
    0.28
    POSITIVE LOGITS
     ialah
    0.46
     যদিও
    0.44
     রাখিয়া
    0.41
     থাকিলেও
    0.40
     wanneer
    0.39
     ইহা
    0.38
     हमरे
    0.38
     ആദ്യം
    0.37
    儅
    0.37
    যদিও
    0.37
    Activations Density 0.012%

    No Known Activations