© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63261
    Prev
    Next
    INDEX
    Explanations

    radio and TV hosts

    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
    СЯ
    -0.91
    上映
    -0.91
    itoare
    -0.85
     playwright
    -0.82
    ప్
    -0.81
    сл
    -0.80
    сяг
    -0.79
    lysses
    -0.77
    $('.
    -0.76
    ర్య
    -0.76
    POSITIVE LOGITS
     broadcast
    1.60
     broadcasting
    1.58
     Broadcasting
    1.41
     hosting
    1.38
    broadcast
    1.35
     ratings
    1.32
    hosting
    1.31
     viewers
    1.30
    主持
    1.29
     host
    1.27
    Activations Density 0.044%

    No Known Activations