© 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. 34-GEMMASCOPE-RES-131K
    7. 60651
    Prev
    Next
    INDEX
    Explanations

    new submitted

    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_34/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
    宜しくお願い
    -0.75
    分け
    -0.73
    んび
    -0.72
    ссов
    -0.72
     técnicas
    -0.71
     even
    -0.71
     classifica
    -0.70
     leyendas
    -0.70
     Его
    -0.68
     technique
    -0.68
    POSITIVE LOGITS
    DoubleQuotes
    0.95
    ">−
    0.91
     بيها
    0.89
     játék
    0.85
     IPv
    0.85
    ggling
    0.85
     һәм
    0.84
     possam
    0.84
     když
    0.84
    adds
    0.84
    Activations Density 0.001%

    No Known Activations