© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31414
    Prev
    Next
    INDEX
    Explanations

    foreign language 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_34/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
     frigor
    -0.77
     their
    -0.76
     perna
    -0.74
     fuma
    -0.73
    各国
    -0.71
     sehr
    -0.71
    INTERFACE
    -0.70
    ！
    -0.69
     aasta
    -0.69
    ärzt
    -0.69
    POSITIVE LOGITS
     compéti
    0.85
     berech
    0.84
     estuche
    0.81
     necesarios
    0.81
     grün
    0.80
     كال
    0.79
     dimensión
    0.78
     weich
    0.77
    urdu
    0.76
     casais
    0.76
    Activations Density 0.000%

    No Known Activations