© 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. 99520
    Prev
    Next
    INDEX
    Explanations

    sports fields and facilities

    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
     연결
    -0.78
     censored
    -0.70
    Fahren
    -0.69
     stereotyp
    -0.69
     humour
    -0.66
    createClass
    -0.65
    夏
    -0.65
    Analog
    -0.65
     Cursor
    -0.65
     علم
    -0.65
    POSITIVE LOGITS
     fields
    1.76
     facilities
    1.73
     facility
    1.69
     complex
    1.39
    complex
    1.29
    fields
    1.28
     Fields
    1.27
     field
    1.25
     indoor
    1.23
     complexes
    1.23
    Activations Density 0.036%

    No Known Activations