© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1624
    Prev
    Next
    INDEX
    Explanations

    United States, daily frequency

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

    The neuron consistently activates on standalone numeric tokens (digits or numbers) in the text.

    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
     after
    -0.95
     constantly
    -0.94
     so
    -0.91
     take
    -0.86
    allclose
    -0.85
    Often
    -0.85
     often
    -0.83
    匯
    -0.81
     becomes
    -0.81
     creates
    -0.81
    POSITIVE LOGITS
     zuge
    0.84
    gar
    0.84
    Gar
    0.82
     moron
    0.81
    טר
    0.81
     CONDITION
    0.81
    散发
    0.80
     rescin
    0.79
     zweier
    0.79
     houve
    0.78
    Activations Density 0.001%

    No Known Activations