© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156114
    Prev
    Next
    INDEX
    Explanations

    charts and data visualizations

    np_acts-logits-general · gemini-2.5-flash-lite

    charts for data visualization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PHYSICAL
    0.47
     kirjo
    0.47
     peritone
    0.47
     motionProxy
    0.46
    لڈ
    0.46
    ActionMode
    0.46
     palav
    0.46
    搔
    0.45
     couro
    0.45
    疥
    0.45
    POSITIVE LOGITS
     chart
    0.92
    chart
    0.92
     Chart
    0.91
    📊
    0.91
    Chart
    0.87
     charted
    0.85
     graphing
    0.80
     charting
    0.80
     CHART
    0.79
     graph
    0.79
    Activations Density 0.044%

    No Known Activations