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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 38
    Prev
    Next
    INDEX
    Explanations

    approximation and range

    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
     $=\
    0.68
     bütün
    0.66
    יית
    0.66
     `{
    0.65
    த்தகைய
    0.65
    धनों
    0.64
     trivially
    0.61
     정말
    0.61
    outed
    0.60
     어떤
    0.60
    POSITIVE LOGITS
    0
    1.34
     onwards
    1.03
     aproximadamente
    0.89
     hingga
    0.86
     నుండి
    0.85
     до
    0.83
    左右
    0.81
     تا
    0.79
    5
    0.76
     sampe
    0.76
    Activations Density 1.739%

    No Known Activations