© 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. 5636
    Prev
    Next
    INDEX
    Explanations

    many, case, ways

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bfs
    0.70
     tunable
    0.70
     fetching
    0.69
    }$(
    0.69
     moved
    0.69
     constricted
    0.68
     different
    0.68
    เชื่อม
    0.68
     frosty
    0.67
    大
    0.66
    POSITIVE LOGITS
    Many
    0.93
     przypadku
    0.87
     Many
    0.75
    许多
    0.74
    叟
    0.72
     повто
    0.72
    िप्स
    0.72
    許多
    0.72
     случае
    0.72
     ብዙ
    0.71
    Activations Density 0.000%

    No Known Activations