© 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. 92188
    Prev
    Next
    INDEX
    Explanations

    regions or sections

    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
     Gainesville
    -0.89
     Merseyside
    -0.89
     जे
    -0.84
     изпол
    -0.82
    ${\
    -0.81
    خیلی
    -0.81
     Varsity
    -0.80
    عکس
    -0.80
    DataBind
    -0.79
     commutative
    -0.78
    POSITIVE LOGITS
     Region
    0.97
     REGION
    0.96
    Region
    0.84
     regions
    0.82
     okaz
    0.80
     Regions
    0.80
     region
    0.79
     Shell
    0.78
     Boot
    0.77
    arsen
    0.76
    Activations Density 0.043%

    No Known Activations