© 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. 20664
    Prev
    Next
    INDEX
    Explanations

    quantity, frequency, effect, time

    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
    本
    0.42
    他在
    0.36
    家族
    0.36
    生成
    0.36
    。
    0.35
    VIDOR
    0.35
    ．
    0.35
    你在
    0.34
    理由
    0.34
    Neural
    0.34
    POSITIVE LOGITS
     খুবই
    0.57
     ძალიან
    0.54
     очень
    0.53
     дуже
    0.52
     વધી
    0.51
     zaidi
    0.50
     cực
    0.48
     rất
    0.48
     thấp
    0.48
     foarte
    0.47
    Activations Density 0.021%

    No Known Activations