© 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. 13637
    Prev
    Next
    INDEX
    Explanations

    andheat, labels, physical

    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
     errori
    -0.97
     possibilities
    -0.96
    طرز
    -0.93
     OTHER
    -0.93
     communications
    -0.93
     señalar
    -0.91
     dettagli
    -0.91
    其他
    -0.91
     posibilidades
    -0.91
     criaturas
    -0.90
    POSITIVE LOGITS
    来源于
    1.00
     Hæ
    0.96
     bucal
    0.94
    0.92
     secondly
    0.91
     Economia
    0.89
    romas
    0.89
    บล
    0.89
     نیز
    0.89
     alfo
    0.89
    Activations Density 0.114%

    No Known Activations