© 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. 13651
    Prev
    Next
    INDEX
    Explanations

    mathematics and math

    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
    ار
    0.74
    م
    0.72
    Кон
    0.71
    V
    0.71
    ᑖ
    0.65
    om
    0.64
     difíc
    0.64
    urm
    0.64
    媝
    0.64
    čí
    0.64
    POSITIVE LOGITS
    าก
    0.79
    ุ
    0.72
     math
    0.70
    s
    0.68
    ู
    0.65
    ัส
    0.64
    ิ่ง
    0.63
    าง
    0.61
    ),"
    0.61
    imized
    0.61
    Activations Density 0.016%

    No Known Activations