© 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. 110672
    Prev
    Next
    INDEX
    Explanations

    Dyson, Peter, api, /**

    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
    برة
    -0.75
     stärker
    -0.72
     considerably
    -0.71
     often
    -0.68
     ever
    -0.68
    Qx
    -0.68
    يبة
    -0.65
     Verwendung
    -0.65
     Disposable
    -0.65
    para
    -0.64
    POSITIVE LOGITS
     Dyson
    1.20
    CFD
    0.90
    diert
    0.88
    tså
    0.86
     dezelve
    0.85
    engineered
    0.84
     engineered
    0.84
    Вт
    0.82
    ANIM
    0.82
    Iacute
    0.82
    Activations Density 0.010%

    No Known Activations