© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6752
    Prev
    Next
    INDEX
    Explanations

    option indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     úlo
    0.66
    渭
    0.64
    ුවන්
    0.62
    莘
    0.61
     கணி
    0.60
    虢
    0.60
    duk
    0.59
    碌
    0.59
     मतदाता
    0.58
    วน
    0.58
    POSITIVE LOGITS
     panelists
    0.75
    revolutionary
    0.74
    فیلم
    0.72
     GALLERY
    0.70
    பாவ
    0.67
    बीच
    0.67
     Panels
    0.67
     kap
    0.67
     horizontally
    0.67
     chied
    0.66
    Activations Density 0.211%

    No Known Activations