© 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-65K
    7. 8858
    Prev
    Next
    INDEX
    Explanations

    Let $ variables

    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
    Negative Logits
    œil
    0.90
    ➣
    0.85
    ﾈ
    0.84
    ரைய
    0.83
    პი
    0.81
     όπου
    0.76
    做到
    0.75
    ത്മ
    0.74
     Businessman
    0.74
    ☞
    0.73
    POSITIVE LOGITS
     denotes
    0.80
     désigne
    0.76
     rgba
    0.70
     integer
    0.64
     subscript
    0.63
     subscripts
    0.62
     grad
    0.62
     $*$
    0.62
    сар
    0.61
    需要在
    0.61
    Activations Density 0.081%

    No Known Activations