© 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
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 3474
    Prev
    Next
    INDEX
    Explanations

    checking input validity

    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_17_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
    uyoruz
    0.80
    ↵↵
    0.72
     buttermilk
    0.71
     jūn
    0.69
     ==
    0.68
     zoveel
    0.68
    imètres
    0.67
    cnf
    0.67
    owały
    0.66
    ulators
    0.65
    POSITIVE LOGITS
     agencia
    0.77
    ,
    0.75
    ,“
    0.75
    电子商务
    0.72
    “
    0.72
    ای
    0.70
    нансо
    0.69
     culinary
    0.68
    Australian
    0.67
     experi
    0.67
    Activations Density 0.115%

    No Known Activations