© 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. 10510
    Prev
    Next
    INDEX
    Explanations

    revenues

    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
    and
    -2.67
    และ
    -2.61
    
    -2.56
    葙
    -2.50
     rusa
    -2.45
    Most
    -2.39
    One
    -2.38
    Because
    -2.34
    }
    -2.34
    Other
    -2.33
    POSITIVE LOGITS
     "
    2.72
     $\
    2.25
     şimdi
    2.23
    太太
    2.20
     empieza
    2.11
    rapeau
    1.98
     ("
    1.97
    一定是
    1.95
     "[
    1.95
     '
    1.94
    Activations Density 0.002%

    No Known Activations