© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 255
    Prev
    Next
    INDEX
    Explanations

    SE model numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    ochemical
    0.58
     after
    0.58
     not
    0.57
    conservation
    0.57
     megt
    0.55
     RESULTS
    0.55
    课
    0.55
    சிய
    0.54
    צ
    0.54
    Account
    0.54
    POSITIVE LOGITS
     chipset
    1.10
     系列
    1.01
     시리즈
    1.00
     Riviera
    0.98
    シリーズ
    0.98
     fiasco
    0.98
    系列
    0.98
     дизайна
    0.95
     firmware
    0.93
     출시
    0.90
    Activations Density 0.807%

    No Known Activations