© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26108
    Prev
    Next
    INDEX
    Explanations

    Jordan and follow-up phrases

    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
    纮
    -2.63
     форми
    -2.63
    瑨
    -2.47
    
    -2.42
    玆
    -2.39
     Now
    -2.38
     decorar
    -2.36
    蕻
    -2.36
     but
    -2.34
     самая
    -2.34
    POSITIVE LOGITS
    牁
    2.78
    さらに
    2.67
    Only
    2.56
    Just
    2.55
    In
    2.55
    3
    2.52
    5
    2.52
    What
    2.50
    6
    2.47
    Too
    2.44
    Activations Density 0.011%

    No Known Activations