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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 815
    Prev
    Next
    INDEX
    Explanations

    export

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     よる
    0.44
     واپسی
    0.41
     Returns
    0.41
     забруд
    0.40
    瓔
    0.39
     détermination
    0.38
    㷌
    0.37
    頂き
    0.36
     hyaluronic
    0.36
     heparin
    0.36
    POSITIVE LOGITS
    export
    1.14
     export
    1.09
     exporting
    0.81
     Export
    0.80
     exported
    0.80
     exports
    0.73
    Export
    0.68
     exporter
    0.67
     Exports
    0.66
    exported
    0.66
    Activations Density 0.002%

    No Known Activations