© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3002
    Prev
    Next
    INDEX
    Explanations

    distinct concepts and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     méridionale
    0.29
     dikdört
    0.28
     Toolbar
    0.28
     ukulele
    0.28
    ωτερ
    0.28
    㬹
    0.27
     Updater
    0.26
     onderwerp
    0.26
     તરી
    0.26
     తిన
    0.26
    POSITIVE LOGITS
     wodurch
    0.36
     mantiene
    0.34
     evitando
    0.34
    reduce
    0.33
     menghindari
    0.33
     zaidi
    0.33
     processo
    0.32
     reduces
    0.30
     avoiding
    0.30
     ಪ
    0.30
    Activations Density 0.199%

    No Known Activations