© 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. 117302
    Prev
    Next
    INDEX
    Explanations

    cheer

    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
     bữa
    -1.03
     acutely
    -0.97
     fonctionnalité
    -0.93
     attaque
    -0.90
     abnormally
    -0.89
     gewähr
    -0.87
    Underlying
    -0.87
     технологий
    -0.85
     Esses
    -0.85
    歓迎
    -0.84
    POSITIVE LOGITS
     Cheer
    1.80
     cheer
    1.70
    leading
    1.25
    Cheer
    1.23
    cheer
    1.19
    ios
    1.15
     cheered
    1.12
     cheering
    1.10
     cheers
    1.02
     CHE
    0.96
    Activations Density 0.005%

    No Known Activations