© 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. 83775
    Prev
    Next
    INDEX
    Explanations

    auto actions

    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
     It
    -1.73
     that
    -1.66
    躋
    -1.63
     which
    -1.58
     is
    -1.56
    igia
    -1.55
     As
    -1.49
     сказала
    -1.48
     In
    -1.47
     wenigen
    -1.47
    POSITIVE LOGITS
     of
    2.20
     置物
    1.95
     gouttes
    1.84
    Välisling
    1.76
     a
    1.67
     entidade
    1.66
    WAUKEE
    1.64
    皤
    1.62
     ſtate
    1.62
    ᷆
    1.59
    Activations Density 0.066%

    No Known Activations