© 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. 30791
    Prev
    Next
    INDEX
    Explanations

    color filters

    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
     Measuring
    0.45
     conducta
    0.42
    getter
    0.41
     hurling
    0.39
     measuring
    0.39
    न्यास
    0.38
     behavior
    0.38
    鷸
    0.38
     Behavior
    0.37
     comportamiento
    0.37
    POSITIVE LOGITS
     filters
    1.14
     filter
    1.03
    Filters
    1.02
    filters
    0.99
    filter
    0.98
     Filters
    0.97
    フィルター
    0.94
     filtros
    0.94
    滤
    0.93
    Filter
    0.92
    Activations Density 0.021%

    No Known Activations