© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66617
    Prev
    Next
    INDEX
    Explanations

    file paths and icons

    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
     frauen
    -1.05
     offrent
    -1.00
    лением
    -0.96
     kommende
    -0.96
     متخصص
    -0.94
    通过
    -0.93
    Nuorodos
    -0.93
    relativeTime
    -0.90
    Filmography
    -0.90
     nawr
    -0.89
    POSITIVE LOGITS
     our
    1.05
     logos
    0.94
     logo
    0.91
    Einf
    0.88
    报警
    0.88
     ſi
    0.86
     waving
    0.86
     fronteras
    0.85
     longtime
    0.84
    ᅳ
    0.84
    Activations Density 0.013%

    No Known Activations