© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    researchers' names and citations

    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
    权力
    0.31
     паліты
    0.29
     باہنی
    0.29
    名词
    0.29
    酺
    0.28
     мир
    0.28
    利润
    0.28
     грошы
    0.28
    经纪
    0.28
     నగ
    0.27
    POSITIVE LOGITS
     researchers
    0.45
     research
    0.40
     collaborators
    0.40
     computational
    0.39
    {\'
    0.39
     computationally
    0.38
     doctoral
    0.37
     experimental
    0.37
     bioinformatics
    0.35
     zebrafish
    0.34
    Activations Density 0.018%

    No Known Activations