© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2437
    Prev
    Next
    INDEX
    Explanations

    eye gaze and contact

    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_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
    .[
    0.72
    TouchUpInside
    0.72
    Edit
    0.70
    놨
    0.70
    িলারা
    0.68
    udarstvennyj
    0.67
    ऑक्साइड
    0.67
     কোন্‌
    0.66
    ⠄
    0.66
    บริหาร
    0.66
    POSITIVE LOGITS
     lhe
    1.59
     ihe
    1.38
     thc
    1.38
     fhe
    1.26
    lhe
    1.20
    㝌
    1.19
    僟
    1.17
    䯩
    1.16
     ln
    1.12
     oll
    1.10
    Activations Density 0.110%

    No Known Activations