© 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. 3429
    Prev
    Next
    INDEX
    Explanations

    consult with legal professionals

    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
    Pagination
    0.69
    Batch
    0.69
    unia
    0.68
    批量
    0.66
     vivo
    0.65
    )]^{
    0.64
    Experiment
    0.63
    precipitation
    0.63
    统治
    0.63
    収
    0.63
    POSITIVE LOGITS
     lawyer
    2.52
     attorney
    2.51
     lawyers
    2.36
     attorneys
    2.34
     consultants
    2.25
     Lawyer
    2.19
     consultant
    2.17
    律师
    2.16
     advisors
    2.15
     advisor
    2.14
    Activations Density 0.191%

    No Known Activations