© 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. 22-GEMMASCOPE-RES-131K
    7. 127789
    Prev
    Next
    INDEX
    Explanations

    UI layout navigation

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Kości
    -1.19
    子さん
    -1.14
     lavable
    -1.08
     chargement
    -1.07
    envolvimento
    -1.06
     experimentar
    -1.06
     bautizo
    -1.06
     Lettres
    -1.05
    deve
    -1.05
     Libros
    -1.05
    POSITIVE LOGITS
    EOUS
    1.18
    关心
    1.17
     prová
    1.13
    Merkmale
    1.06
    ICOLON
    1.04
    nibus
    1.03
     gluing
    1.03
     waż
    1.02
    lineno
    1.02
    ЕН
    1.02
    Activations Density 0.001%

    No Known Activations