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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12960
    Prev
    Next
    INDEX
    Explanations

    APA, Association, AGA citations

    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_10/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
    selbe
    -3.02
     have
    -2.56
    大概
    -2.52
     Their
    -2.52
     Garantía
    -2.41
    '
    -2.41
    相当
    -2.39
     широкий
    -2.39
    
    -2.30
    霂
    -2.27
    POSITIVE LOGITS
            
    2.80
    を除
    2.50
    最初は
    2.39
    section
    2.36
    激しい
    2.34
    紆
    2.27
    がんば
    2.25
    主役
    2.23
     неожидан
    2.22
    ついで
    2.20
    Activations Density 0.006%

    No Known Activations