© 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. 8521
    Prev
    Next
    INDEX
    Explanations

    series, designed, route, Qe

    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
    Other
    0.96
    Map
    0.94
    An
    0.84
    F
    0.84
    other
    0.83
    Bin
    0.82
    V
    0.81
    B
    0.80
    math
    0.80
    Market
    0.79
    POSITIVE LOGITS
     upholding
    1.07
     combating
    1.07
     pesticide
    1.05
     warfare
    1.04
     rejoicing
    1.03
     turnovers
    1.03
    䨋
    1.03
     pharmaceuticals
    1.03
     Fabrication
    1.02
     tetrachloride
    1.01
    Activations Density 0.000%

    No Known Activations