© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2666
    Prev
    Next
    INDEX
    Explanations

    shell commands and code

    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_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рово
    1.44
    ́ch
    1.42
     ihe
    1.41
    isierte
    1.40
    ებული
    1.37
     теркәлүсез
    1.37
    ة
    1.35
     provision
    1.33
    פרי
    1.33
     consec
    1.32
    POSITIVE LOGITS
    g
    2.11
     annoyed
    1.65
    p
    1.63
     yelling
    1.61
    nYou
    1.59
    j
    1.59
    il
    1.59
    n
    1.55
     раздра
    1.54
     mumbled
    1.44
    Activations Density 0.216%

    No Known Activations