© 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. 128158
    Prev
    Next
    INDEX
    Explanations

    identifiers in paths

    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
    norsk
    -0.98
     quella
    -0.98
     mūsų
    -0.93
     गर्न
    -0.93
     neuve
    -0.91
    ()))
    -0.89
     provato
    -0.89
     gydy
    -0.89
     Verantwortung
    -0.88
     šo
    -0.87
    POSITIVE LOGITS
     then
    1.23
    过来的
    0.95
    าสตร์
    0.93
    両親
    0.90
    надца
    0.89
    抡
    0.88
     plus
    0.85
    陸上
    0.84
    izaron
    0.84
     hereinafter
    0.83
    Activations Density 0.106%

    No Known Activations