© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64648
    Prev
    Next
    INDEX
    Explanations

    stages and midpoints

    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
     Française
    -0.84
    ᵖ
    -0.83
    Č
    -0.77
     サッカー
    -0.76
    Debugger
    -0.76
    Dequeue
    -0.75
    МЕН
    -0.75
    кса
    -0.75
     السن
    -0.75
     نمایش
    -0.74
    POSITIVE LOGITS
     realm
    1.78
     ninth
    1.36
     peak
    1.35
     Realm
    1.24
    Peak
    1.20
     late
    1.14
     powerhouse
    1.11
     Peak
    1.07
     eighth
    1.06
    peak
    1.05
    Activations Density 0.003%

    No Known Activations