© 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. 91130
    Prev
    Next
    INDEX
    Explanations

    sports context

    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
     menangkap
    -0.99
    endió
    -0.98
     sugerencias
    -0.96
    {})
    -0.96
     eredeti
    -0.92
    SUITE
    -0.92
     "'");
    -0.89
     És
    -0.89
     встроен
    -0.88
     membuat
    -0.88
    POSITIVE LOGITS
     preparations
    1.09
     playing
    1.02
     mentally
    1.02
     experienced
    0.98
     injuries
    0.96
     injury
    0.94
     psychologically
    0.93
     combinations
    0.90
     players
    0.89
     regroup
    0.88
    Activations Density 0.007%

    No Known Activations