© 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. 7119
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    convex
    0.55
    txt
    0.54
    bool
    0.52
     equipments
    0.51
    өп
    0.50
    pixels
    0.50
    }))
    0.49
     ihm
    0.49
    loader
    0.48
    })"
    0.48
    POSITIVE LOGITS
     perhaps
    0.72
    ੇ
    0.67
     questa
    0.64
     forse
    0.64
     這
    0.64
     buna
    0.63
     何
    0.62
     Ра
    0.61
     Inggris
    0.61
    弜
    0.60
    Activations Density 0.006%

    No Known Activations