© 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. 65228
    Prev
    Next
    INDEX
    Explanations

    spokesman or spokesperson followed by name/title

    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
    中村
    -0.84
     مشاور
    -0.74
     красота
    -0.74
    ferenz
    -0.72
     בין
    -0.72
    وزن
    -0.72
     amazement
    -0.71
    рт
    -0.71
     椅子
    -0.71
     eser
    -0.69
    POSITIVE LOGITS
     spokesman
    1.86
     spokesperson
    1.66
     spokeswoman
    1.50
     Spokes
    1.41
    media
    1.38
     media
    1.34
     communications
    1.30
     spokes
    1.29
    MEDIA
    1.22
     MEDIA
    1.21
    Activations Density 0.035%

    No Known Activations