© 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. 22-GEMMASCOPE-RES-131K
    7. 38987
    Prev
    Next
    INDEX
    Explanations

    login session redirection

    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_22/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
     perſ
    -0.94
     diſt
    -0.92
    嘁
    -0.89
     هؤلاء
    -0.88
     nästan
    -0.87
    たぶん
    -0.86
     苹果
    -0.86
    ほんと
    -0.86
     faisaient
    -0.86
     kablo
    -0.85
    POSITIVE LOGITS
     with
    1.34
    蛾
    1.02
    olisme
    1.01
     re
    0.98
     failed
    0.94
     before
    0.93
     bad
    0.93
     nifty
    0.93
    violet
    0.91
    ֶּ
    0.91
    Activations Density 0.001%

    No Known Activations