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-262K
    4. 52882
    Prev
    Next
    INDEX
    Explanations

    a single person

    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_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
     );//
    0.80
     //
    0.78
     мелдеш
    0.75
     lymphatiques
    0.74
     {//
    0.72
    ."—
    0.71
    ૐ
    0.71
    ൯
    0.70
     inférieurs
    0.70
    らなかった
    0.70
    POSITIVE LOGITS
     whi
    1.59
     Thi
    1.41
     wi
    1.26
     Whi
    1.22
    Whi
    1.21
     th
    1.20
     thi
    1.19
     hea
    1.18
    Ƅ
    1.17
    -...
    1.17
    Activations Density 0.000%

    No Known Activations