© 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-65K
    7. 17258
    Prev
    Next
    INDEX
    Explanations

    magic, civilization, dimensional

    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_65k_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
    ق
    0.58
    ক
    0.53
    ص
    0.48
    는
    0.48
    어
    0.48
    is
    0.47
    나
    0.46
    I
    0.46
    ح
    0.44
    Sens
    0.43
    POSITIVE LOGITS
     отделения
    0.53
    ៦
    0.52
     ivvu
    0.52
     hatchery
    0.51
    ៧
    0.50
     slush
    0.49
    elni
    0.49
    ৬৫
    0.48
    ៨
    0.47
    palette
    0.47
    Activations Density 0.008%

    No Known Activations