© 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. 64560
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
     that
    -1.73
     maybe
    -1.60
     mainly
    -1.57
     since
    -1.56
     someone
    -1.52
     knew
    -1.50
     something
    -1.50
     different
    -1.45
     sometimes
    -1.45
     what
    -1.43
    POSITIVE LOGITS
     dieser
    1.35
     hierdie
    1.34
     }));
    1.23
     เว
    1.16
    镍
    1.16
    swal
    1.16
     यह
    1.16
    므
    1.15
     canadien
    1.15
     วิ
    1.15
    Activations Density 0.041%

    No Known Activations