© 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. 8678
    Prev
    Next
    INDEX
    Explanations

    than

    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
     Enzyme
    0.95
     금융
    0.94
     genomics
    0.93
     Inorganic
    0.90
     Metadata
    0.89
     Genomics
    0.89
     Electrochemical
    0.86
    <unused476>
    0.85
     Ecosystem
    0.84
     Serviço
    0.84
    POSITIVE LOGITS
     jeans
    0.92
     saucepan
    0.91
     Mustangs
    0.90
     aunt
    0.89
     witches
    0.86
     peasant
    0.85
     apartments
    0.85
     granny
    0.84
    jack
    0.84
     poodle
    0.82
    Activations Density 0.341%

    No Known Activations