© 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. 10-GEMMASCOPE-RES-131K
    7. 99616
    Prev
    Next
    INDEX
    Explanations

    detecting the word "report"

    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
     (
    -2.17
     и
    -1.92
     '
    -1.90
     $\
    -1.76
    },
    -1.75
    ."
    -1.74
     $
    -1.72
    }
    -1.72
     $(
    -1.70
    ↵↵
    -1.64
    POSITIVE LOGITS
     reports
    1.98
    きちんと
    1.98
    –¿
    1.91
    ant
    1.85
     devono
    1.83
     REPORTS
    1.80
    продам
    1.80
    ⚫
    1.76
     Reports
    1.76
     potrebbe
    1.73
    Activations Density 0.089%

    No Known Activations