© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1257
    Prev
    Next
    INDEX
    Explanations

    American followed by history, revolution, culture

    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_16_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
    د
    1.04
    س
    1.01
    д
    0.89
    도
    0.86
    в
    0.84
    та
    0.84
    ج
    0.84
    ك
    0.84
    ف
    0.81
    在
    0.80
    POSITIVE LOGITS
    ized
    0.68
     I
    0.64
    Ｉ
    0.63
    ;
    0.59
    ur
    0.58
     American
    0.57
    izing
    0.55
    il
    0.55
    ği
    0.54
    }))
    0.54
    Activations Density 0.009%

    No Known Activations