© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 69759
    Prev
    Next
    INDEX
    Explanations

    sample collected or taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
     internalization
    1.85
    oculars
    1.77
    派出
    1.72
    ologist
    1.71
     subspecies
    1.69
     alis
    1.68
    ologists
    1.66
    諜
    1.66
    idence
    1.64
     spies
    1.63
    POSITIVE LOGITS
     Сла
    1.05
    Void
    1.01
    สู
    0.98
    מק
    0.95
     Гре
    0.95
    닉
    0.95
    ބ
    0.94
    refund
    0.94
     Sunni
    0.93
     Void
    0.93
    Activations Density 0.000%

    No Known Activations