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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103864
    Prev
    Next
    INDEX
    Explanations

    foreign language and numbers

    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
     Propor
    -0.75
     defStyle
    -0.73
    ulam
    -0.72
     Polskiego
    -0.71
     GROSS
    -0.70
    ⁨
    -0.69
    myr
    -0.68
     sélectionnés
    -0.68
     conical
    -0.67
    propor
    -0.66
    POSITIVE LOGITS
    vida
    0.71
    atalos
    0.68
     продукт
    0.68
    ###
    0.67
    ???
    0.66
     Leopold
    0.64
    vidas
    0.63
     आप
    0.61
    Тре
    0.61
    違
    0.60
    Activations Density 0.075%

    No Known Activations