© 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. 82428
    Prev
    Next
    INDEX
    Explanations

    competitive figure skater

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on numeric tokens (years, dates, scores, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    最近の
    -1.03
    ！（
    -1.01
    Recently
    -1.01
     Recently
    -0.97
     recently
    -0.96
    Usually
    -0.96
    最近
    -0.95
     desmotiv
    -0.94
     now
    -0.94
     Usually
    -0.91
    POSITIVE LOGITS
     insanely
    1.09
     hugely
    1.05
     acclaimed
    1.05
     incredibly
    1.02
     renowned
    0.99
    />
    0.99
    set
    0.98
    ङ्
    0.97
     ridiculously
    0.96
     ചെയ
    0.96
    Activations Density 0.017%

    No Known Activations