© 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. 8659
    Prev
    Next
    INDEX
    Explanations

    javascript import/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
    }--\
    0.48
     Geschwindigkeit
    0.46
     substring
    0.44
    飲料
    0.44
     кожу
    0.44
    駒
    0.43
     говорили
    0.43
     eingeb
    0.41
    樞
    0.41
    betriebnahme
    0.41
    POSITIVE LOGITS
     export
    1.11
     exports
    1.09
     exported
    1.06
     exporting
    0.96
    export
    0.93
     Export
    0.91
     Exports
    0.89
     import
    0.80
     exporters
    0.80
    exports
    0.79
    Activations Density 0.014%

    No Known Activations