© 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. 31020
    Prev
    Next
    INDEX
    Explanations

    Wolverhampton Wanderers and football clubs

    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
    Karakteristik
    -0.79
     Rima
    -0.77
     Derry
    -0.74
    Optimized
    -0.74
     optimized
    -0.72
     Observation
    -0.70
     Slovenia
    -0.70
     Tamil
    -0.70
     centralized
    -0.69
     optimizing
    -0.68
    POSITIVE LOGITS
     Wolverhampton
    1.41
     Wolves
    1.08
    狼
    1.04
    🐺
    0.96
    WOL
    0.94
    Wolves
    0.92
    hampton
    0.88
     wolves
    0.87
     howl
    0.85
     Nuno
    0.82
    Activations Density 0.014%

    No Known Activations