© 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. 31-GEMMASCOPE-2-RES-262K
    7. 100287
    Prev
    Next
    INDEX
    Explanations

    chess, BERT, tenant, gas, strut

    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_31_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
    га
    0.46
    sink
    0.46
    espresso
    0.46
    gap
    0.44
    었습니다
    0.44
    usion
    0.44
    iane
    0.43
    و
    0.43
    릅
    0.43
    ir
    0.43
    POSITIVE LOGITS
     ajust
    0.54
     ajustar
    0.51
     Craft
    0.51
     alcool
    0.50
     控制
    0.49
     Zeus
    0.49
     Lambda
    0.48
     Κ
    0.48
     Called
    0.47
     luas
    0.47
    Activations Density 0.006%

    No Known Activations