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. 9-GEMMASCOPE-2-RES-262K
    4. 7560
    Prev
    Next
    INDEX
    Explanations

    appendix

    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_9_width_262k_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
    tte
    2.26
     собой
    2.23
     పాటు
    2.22
     Fransiya
    2.10
     Sury
    2.10
    %%%%%%%%%%%%%%%%
    1.95
    न
    1.94
    aneous
    1.94
    س
    1.93
    кий
    1.91
    POSITIVE LOGITS
    ை
    2.33
    ु
    2.17
    ਣ
    2.12
    𝕟
    2.06
    و
    2.03
    та
    1.96
    𝕡
    1.94
    𝕣
    1.88
    м
    1.85
    ну
    1.84
    Activations Density 0.000%

    No Known Activations