© 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. 90499
    Prev
    Next
    INDEX
    Explanations

    Slovenian language

    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
     Arn
    -0.82
     Cru
    -0.82
    ecu
    -0.80
    ״
    -0.79
     Promise
    -0.77
    (",",
    -0.75
    mern
    -0.75
     inicios
    -0.75
     overcrowded
    -0.75
     î
    -0.73
    POSITIVE LOGITS
    junct
    0.77
     znaj
    0.75
     jamur
    0.72
    ēj
    0.71
     thank
    0.70
     getSystem
    0.69
    эль
    0.68
    Altre
    0.68
     麺
    0.66
    茫
    0.66
    Activations Density 0.016%

    No Known Activations