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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 41317
    Prev
    Next
    INDEX
    Explanations

    anti-malware

    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
    discrimin
    0.81
     franqu
    0.81
     moduleId
    0.81
     ఆరోగ్య
    0.77
    歼
    0.77
     virulence
    0.77
    ρα
    0.77
    バトル
    0.77
     কর্মক
    0.76
     сла
    0.76
    POSITIVE LOGITS
    െന്നും
    0.67
    amac
    0.57
     echo
    0.57
    ॉर्म
    0.55
    改善
    0.55
    जूदा
    0.54
    씀
    0.54
     structure
    0.54
    çç
    0.54
    减少
    0.53
    Activations Density 0.003%

    No Known Activations