© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45686
    Prev
    Next
    INDEX
    Explanations

    by, Baltimore, Mass, Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     any
    -1.40
     любой
    -1.20
     nuestros
    -1.20
    ish
    -1.18
     nuestro
    -1.16
     qualsiasi
    -1.14
    isser
    -1.13
     podían
    -1.13
     cualquiera
    -1.13
     любы
    -1.11
    POSITIVE LOGITS
     finally
    1.53
    鉿
    1.46
     it
    1.45
     república
    1.45
     opinião
    1.41
     disregarding
    1.41
     culminating
    1.39
     promove
    1.38
    一辆
    1.35
     a
    1.34
    Activations Density 0.000%

    No Known Activations