© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5725
    Prev
    Next
    INDEX
    Explanations

    mathematical solutions

    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_17_width_16k_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
    헉
    0.82
    recursion
    0.77
     again
    0.72
    kannya
    0.71
     tentu
    0.70
    i
    0.69
    banking
    0.68
    涙
    0.68
    --;
    0.67
    を見
    0.66
    POSITIVE LOGITS
    𝐶
    1.10
    มีการ
    0.99
     claves
    0.94
    ʟ
    0.94
     possèdent
    0.94
    Các
    0.93
     Các
    0.92
     utilisez
    0.90
    𝐷
    0.90
    ланган
    0.90
    Activations Density 0.136%

    No Known Activations