© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91600
    Prev
    Next
    INDEX
    Explanations

    lead roles / rights reserved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cân
    -0.80
     Huy
    -0.77
     day
    -0.73
    ʒ
    -0.73
    Jane
    -0.71
     Kane
    -0.68
    ǝ
    -0.66
    嶺
    -0.65
    compiler
    -0.65
    eclipse
    -0.65
    POSITIVE LOGITS
     Lc
    0.77
     madison
    0.76
    ┯
    0.75
    нін
    0.74
     Fn
    0.72
    视为
    0.71
    sedur
    0.70
     MOB
    0.70
     reachable
    0.70
     электро
    0.69
    Activations Density 0.012%

    No Known Activations