Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 6051
    Prev
    Next
    INDEX
    Explanations

    九九乘法表

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    宵
    0.74
     वाक्यांश
    0.73
     Branches
    0.73
     branches
    0.72
     BRANCH
    0.72
     branch
    0.72
     الطفل
    0.71
     zakon
    0.71
     nightlife
    0.70
    瘾
    0.70
    POSITIVE LOGITS
     matrix
    3.36
     matrices
    3.15
    矩阵
    3.11
     Matrix
    3.10
    Matrix
    3.08
    matrix
    3.06
     Matrices
    2.74
    matrices
    2.70
     матри
    2.56
    Matrices
    2.56
    Activations Density 0.469%

    No Known Activations