© 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. 99032
    Prev
    Next
    INDEX
    Explanations

    just followed by a verb

    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
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -2.13
     jenen
    -1.37
     Dimensiones
    -1.35
    たの
    -1.35
     jenem
    -1.34
     véritable
    -1.34
    を変える
    -1.33
    迨
    -1.33
    CONTENIDO
    -1.33
    鈣
    -1.30
    POSITIVE LOGITS
     получает
    1.52
    менение
    1.41
    atórios
    1.35
    慜
    1.34
    звание
    1.28
    「
    1.27
     знал
    1.26
     питання
    1.24
    queeze
    1.23
    I
    1.22
    Activations Density 0.012%

    No Known Activations