© 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. 17-GEMMASCOPE-2-RES-16K
    7. 8684
    Prev
    Next
    INDEX
    Explanations

    adding or supplementing

    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_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     vague
    0.77
    twice
    0.76
     bizarre
    0.75
     ominous
    0.75
    legte
    0.74
    gown
    0.73
     mask
    0.72
    weird
    0.72
     ظ
    0.72
    alleg
    0.72
    POSITIVE LOGITS
     添加
    1.23
     Adds
    1.23
     adicionar
    1.16
     menambahkan
    1.16
     adicion
    1.15
    Adds
    1.14
     adds
    1.13
     допол
    1.09
     ergän
    1.09
     Adding
    1.09
    Activations Density 0.074%

    No Known Activations