© 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. 8673
    Prev
    Next
    INDEX
    Explanations

    strict mode in code

    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
     uniforme
    0.94
    БА
    0.93
    ically
    0.91
    cycle
    0.89
    scrollTo
    0.89
    chauff
    0.86
    dde
    0.86
     कुल
    0.85
    ו
    0.84
     Carta
    0.83
    POSITIVE LOGITS
     strictest
    0.97
    堈
    0.92
    પણે
    0.81
     liability
    0.80
    ை
    0.78
     rationing
    0.77
     RPC
    0.77
     neighborhoods
    0.77
     LIABILITY
    0.77
     forbid
    0.75
    Activations Density 0.004%

    No Known Activations