© 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. 32924
    Prev
    Next
    INDEX
    Explanations

    foreign and Japanese verb endings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    T
    -2.13
    u
    -2.13
    N
    -2.09
    j
    -1.88
    F
    -1.80
    b
    -1.73
    g
    -1.70
    r
    -1.69
    A
    -1.69
    v
    -1.66
    POSITIVE LOGITS
     Anſ
    1.69
    酲
    1.67
    汭
    1.63
     Número
    1.59
    淠
    1.55
     asegura
    1.51
     Autó
    1.50
     čím
    1.48
     Projektu
    1.45
     aeroporto
    1.44
    Activations Density 0.001%

    No Known Activations