© 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. 191705
    Prev
    Next
    INDEX
    Explanations

    he proposed

    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
    PluginResult
    0.40
    
    0.39
     republics
    0.38
    setRequest
    0.37
    গ্রামী
    0.37
     Charlton
    0.37
     রোগীদের
    0.37
    ()%
    0.37
    TGF
    0.37
    indigo
    0.36
    POSITIVE LOGITS
     caderno
    0.39
     contém
    0.39
     автомо
    0.38
     LP
    0.38
     ED
    0.38
     disagreed
    0.38
     zawiera
    0.38
     recoup
    0.37
     wspom
    0.37
     tempt
    0.37
    Activations Density 0.000%

    No Known Activations