© 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. 6971
    Prev
    Next
    INDEX
    Explanations

    race names, company names, specific people

    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
    変わらず
    -1.66
    お父
    -1.65
     dejando
    -1.63
    が違う
    -1.55
    れたら
    -1.54
    一丝
    -1.52
     @"/
    -1.51
     Añade
    -1.51
    神情
    -1.51
     zwięks
    -1.48
    POSITIVE LOGITS
    6
    1.77
    0
    1.70
    是
    1.64
    8
    1.62
    3
    1.62
    4
    1.56
    特的
    1.46
    都
    1.46
     what
    1.39
     Because
    1.39
    Activations Density 0.056%

    No Known Activations