© 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. 38554
    Prev
    Next
    INDEX
    Explanations

    java method calls

    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
     münchen
    -1.63
     themselves
    -1.44
     nimmer
    -1.43
    tarta
    -1.40
     when
    -1.39
     produisons
    -1.39
    träd
    -1.36
     retten
    -1.34
     galima
    -1.29
     they
    -1.26
    POSITIVE LOGITS
    ANIUM
    1.42
     longo
    1.30
     órg
    1.27
     herói
    1.27
    since
    1.26
     lequel
    1.24
    ciated
    1.20
     être
    1.20
    soit
    1.20
    GRAFÍA
    1.19
    Activations Density 0.027%

    No Known Activations