© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54059
    Prev
    Next
    INDEX
    Explanations

    questions and exclamations

    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
    ágen
    -0.97
    randrange
    -0.95
    龊
    -0.93
    μου
    -0.92
     กรัม
    -0.90
     vorgenommen
    -0.88
    ้งาน
    -0.88
     fordi
    -0.86
    hline
    -0.85
    생
    -0.85
    POSITIVE LOGITS
     or
    1.16
     does
    0.98
     müs
    0.94
    aré
    0.91
     this
    0.90
     могли
    0.89
     I
    0.88
    ?
    0.87
     logotipo
    0.86
     couteau
    0.86
    Activations Density 0.073%

    No Known Activations