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. 1325
    Prev
    Next
    INDEX
    Explanations

    break down relationship

    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
    讀
    0.73
    Ꮼ
    0.70
    acuda
    0.70
    ாளர்க
    0.67
    ლები
    0.66
     ем
    0.65
    读
    0.65
     reads
    0.65
     pedicure
    0.65
    duled
    0.64
    POSITIVE LOGITS
     forearm
    0.74
    阴
    0.74
    IService
    0.73
    아가
    0.72
     ove
    0.70
     搭
    0.69
    Dis
    0.69
     Jericho
    0.69
    OTO
    0.66
    ото
    0.66
    Activations Density 0.000%

    No Known Activations