© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5999
    Prev
    Next
    INDEX
    Explanations

    end-to-end

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     acidic
    0.76
     rog
    0.75
     кле
    0.75
    Ро
    0.74
    혈
    0.74
    Unlock
    0.73
     ES
    0.73
    籍
    0.72
    ंदा
    0.72
     mature
    0.72
    POSITIVE LOGITS
    owment
    1.62
    gült
    1.59
    osulf
    1.54
    angering
    1.48
    orsement
    1.42
    倪
    1.40
    urance
    1.39
     концов
    1.37
    URANCE
    1.37
    osperm
    1.36
    Activations Density 0.069%

    No Known Activations