© 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. 128062
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    !
    -0.95
    varrho
    -0.90
    narod
    -0.89
    shaped
    -0.85
    lysis
    -0.84
     J
    -0.84
    ly
    -0.83
     CONCLUSION
    -0.83
     by
    -0.82
    вает
    -0.82
    POSITIVE LOGITS
    みよう
    0.99
    Technik
    0.98
    Elekt
    0.96
     notor
    0.94
     réussir
    0.94
    Produktion
    0.94
     toolStrip
    0.93
    Nederland
    0.92
     však
    0.91
    Landes
    0.91
    Activations Density 0.015%

    No Known Activations