© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60344
    Prev
    Next
    INDEX
    Explanations

    the word "program"

    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
     suced
    -1.79
     descans
    -1.77
    ⍽
    -1.76
    蒾
    -1.71
     rengi
    -1.65
    ࿙
    -1.61
    ޏ
    -1.59
     feil
    -1.59
     keram
    -1.59
    secara
    -1.56
    POSITIVE LOGITS
     =
    2.05
    In
    1.89
     剤
    1.80
    ;
    1.80
    );
    1.80
    듯
    1.73
     bemerken
    1.66
    廰
    1.63
     überweisen
    1.62
    What
    1.56
    Activations Density 0.041%

    No Known Activations