© 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. 22-GEMMASCOPE-2-RES-65K
    7. 7447
    Prev
    Next
    INDEX
    Explanations

    state of services or establishments

    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_22_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
     workpiece
    0.92
     ใส่
    0.82
     |_{
    0.78
     proteine
    0.76
     fluide
    0.75
    生成
    0.72
     cleavage
    0.71
    ">→</
    0.71
     ট্রেনে
    0.70
     tensile
    0.69
    POSITIVE LOGITS
     located
    1.80
     Located
    1.68
     staffed
    1.65
     시설
    1.59
     설립
    1.57
    located
    1.57
     situated
    1.57
    Located
    1.56
     operated
    1.53
     규모
    1.49
    Activations Density 0.289%

    No Known Activations