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. 41212
    Prev
    Next
    INDEX
    Explanations

    why did the joke

    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
    Pok
    0.78
     wins
    0.78
     pellet
    0.76
     pellets
    0.74
     ባ
    0.73
    үз
    0.69
    Come
    0.69
     Pok
    0.68
    澳门
    0.68
     அழிக்க
    0.67
    POSITIVE LOGITS
    난
    0.66
    ख्त
    0.65
    raints
    0.64
     ct
    0.63
    ֲ
    0.63
     ctr
    0.61
     merah
    0.59
    chr
    0.58
     tová
    0.58
    រស
    0.58
    Activations Density 0.015%

    No Known Activations