© 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. 6801
    Prev
    Next
    INDEX
    Explanations

    cleaning and related issues

    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
     optimal
    -1.23
     стране
    -1.12
    Duel
    -1.11
    handleDelete
    -1.08
     exquisite
    -1.08
     characteristics
    -1.07
    OPHER
    -1.06
     soggy
    -1.06
    lador
    -1.02
     schrijven
    -1.02
    POSITIVE LOGITS
     теперь
    1.25
     nejen
    1.21
     jälkeen
    1.16
     its
    1.12
     δὲ
    1.09
     our
    1.07
     边
    1.06
     qualsiasi
    1.05
     entram
    1.05
    Pág
    1.03
    Activations Density 0.146%

    No Known Activations