© 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. 25848
    Prev
    Next
    INDEX
    Explanations

    details and facts

    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
    yczny
    -0.91
     선택
    -0.90
    laria
    -0.86
     вектора
    -0.80
    Produzione
    -0.80
    Einzelnachweise
    -0.79
     categoryId
    -0.79
    Від
    -0.78
    شهر
    -0.78
    ListOf
    -0.77
    POSITIVE LOGITS
     name
    2.47
     Name
    2.36
    Name
    2.06
     Date
    1.91
     location
    1.84
    NAME
    1.84
    name
    1.77
    Date
    1.73
     NAME
    1.64
     Type
    1.58
    Activations Density 0.234%

    No Known Activations