© 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. 83856
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    并且
    -1.55
    huana
    -1.55
    Also
    -1.45
     schlechte
    -1.42
     people
    -1.42
     also
    -1.41
     for
    -1.41
     також
    -1.39
     what
    -1.38
    これからの
    -1.38
    POSITIVE LOGITS
    1
    1.63
    2
    1.39
     domingos
    1.38
    activa
    1.37
    BeginInit
    1.36
     której
    1.35
    ğından
    1.35
    amaño
    1.34
     znajd
    1.34
    chá
    1.33
    Activations Density 0.036%

    No Known Activations