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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 1376
    Prev
    Next
    INDEX
    Explanations

    maailmanlainen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     Е
    1.00
     Detta
    0.98
     Во
    0.92
    СТ
    0.89
     Vý
    0.89
     bella
    0.88
     Фон
    0.87
    і
    0.87
     Это
    0.86
     Но
    0.86
    POSITIVE LOGITS
     su
    0.67
     mon
    0.59
     u
    0.56
     use
    0.55
     er
    0.55
     hyvin
    0.54
     kes
    0.53
     yks
    0.53
     mahdoll
    0.51
    kin
    0.49
    Activations Density 0.001%

    No Known Activations