© 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
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5142
    Prev
    Next
    INDEX
    Explanations

    open source community

    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
    coefficients
    0.72
     فيلم
    0.70
     coefficients
    0.69
    Pict
    0.66
     cabel
    0.63
    懊
    0.62
    颌
    0.61
     배치
    0.60
    aray
    0.60
    เซล
    0.60
    POSITIVE LOGITS
     community
    1.51
    社区
    1.39
     GitHub
    1.37
     developer
    1.36
     contributors
    1.36
    开源
    1.36
     maintain
    1.32
     open
    1.32
     developers
    1.31
     volunteer
    1.29
    Activations Density 0.874%

    No Known Activations