© 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. 98818
    Prev
    Next
    INDEX
    Explanations

    clock and hardware components

    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
     miejsce
    -0.82
    点的
    -0.81
     Diputados
    -0.78
     العالم
    -0.77
     nagyon
    -0.75
     POR
    -0.75
     likely
    -0.75
     potensi
    -0.74
     usein
    -0.73
    WindowManager
    -0.73
    POSITIVE LOGITS
    xiety
    0.73
     Abteilung
    0.71
    thun
    0.70
    嚷
    0.69
     chon
    0.69
    Ard
    0.69
    verd
    0.68
    ęki
    0.68
     Décembre
    0.66
     Select
    0.66
    Activations Density 0.004%

    No Known Activations