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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13326
    Prev
    Next
    INDEX
    Explanations

    nanowires and transistors

    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_40_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
    akhir
    0.39
    バス
    0.37
     sole
    0.37
     kennt
    0.37
     membership
    0.35
     mains
    0.35
    okol
    0.35
    
    0.35
     ”
    0.35
    דר
    0.34
    POSITIVE LOGITS
     nanom
    0.43
     nanow
    0.43
    :"
    0.41
     "\
    0.40
    -"
    0.39
     okt
    0.39
    蜴
    0.39
     '\
    0.39
     Aniston
    0.39
    PAAm
    0.39
    Activations Density 0.001%

    No Known Activations