© 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-16K
    7. 3222
    Prev
    Next
    INDEX
    Explanations

    list items separated by commas

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     \,,
    0.88
    
    0.84
    urahan
    0.80
     ไหร่
    0.77
    aurant
    0.77
    ঠাকুর
    0.77
     \%$,
    0.76
     খ্র
    0.76
    ല്
    0.74
     (),
    0.74
    POSITIVE LOGITS
    ,
    0.82
    、
    0.80
    |
    0.72
    Progress
    0.70
    かつ
    0.69
     ও
    0.68
     but
    0.68
     &
    0.68
    而
    0.64
     –
    0.64
    Activations Density 0.565%

    No Known Activations