© 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. 69064
    Prev
    Next
    INDEX
    Explanations

    risk assessment and stratification

    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
     to
    -1.70
    }
    -1.66
     wenige
    -1.50
    ヽ
    -1.50
    tling
    -1.48
    t
    -1.45
     would
    -1.45
    derdag
    -1.41
    zehnten
    -1.39
    葙
    -1.38
    POSITIVE LOGITS
     tişört
    1.79
     a
    1.79
     pantolon
    1.63
    がみ
    1.59
    啻
    1.59
    phoric
    1.57
     eşofman
    1.55
    事も
    1.54
     ceket
    1.51
     también
    1.46
    Activations Density 0.011%

    No Known Activations