© 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. 783
    Prev
    Next
    INDEX
    Explanations

    valence electrons

    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
     gauze
    1.22
     leaned
    1.18
     cariño
    1.18
    agnetic
    1.16
     exemplify
    1.12
    selValue
    1.11
     gắn
    1.11
     khắp
    1.11
    othesis
    1.11
    🫢
    1.10
    POSITIVE LOGITS
    तम
    1.16
    ref
    1.10
     सम
    1.04
    line
    1.00
    र
    0.99
    ยัง
    0.99
    u
    0.96
    wehr
    0.96
    л
    0.96
    los
    0.95
    Activations Density 0.000%

    No Known Activations