© 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. 13469
    Prev
    Next
    INDEX
    Explanations

    JSON structure elements

    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
     so
    -0.95
    ">-
    -0.90
    Debido
    -0.88
    carnated
    -0.86
    writeFieldEnd
    -0.83
    luor
    -0.82
    劻
    -0.82
    łania
    -0.82
    plasia
    -0.82
     arī
    -0.82
    POSITIVE LOGITS
    поги
    0.98
     list
    0.88
    IoT
    0.88
     Belich
    0.82
     dilapidated
    0.80
     các
    0.79
    IPv
    0.79
    жня
    0.77
     Moodle
    0.76
     psychiat
    0.76
    Activations Density 0.044%

    No Known Activations