© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65624
    Prev
    Next
    INDEX
    Explanations

    dates and court cases

    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
     Friedrich
    -0.82
     Kong
    -0.82
     perquè
    -0.82
     Gaz
    -0.81
     candidate
    -0.80
    iferous
    -0.79
     mest
    -0.78
     Ralph
    -0.78
     Ки
    -0.77
     ۴
    -0.77
    POSITIVE LOGITS
     pixar
    0.79
     Dm
    0.79
     turkish
    0.78
    Autores
    0.77
     bikers
    0.77
     Req
    0.76
     Elephants
    0.76
     Insomnia
    0.76
    דיה
    0.76
     avengers
    0.75
    Activations Density 0.011%

    No Known Activations