© 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. 102902
    Prev
    Next
    INDEX
    Explanations

    calls abort

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

    The neuron detects numerical tokens (digits and 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
    PBS
    -0.77
    kuro
    -0.73
    ifeng
    -0.73
    ペル
    -0.71
     Frühstück
    -0.71
     delaying
    -0.70
     verpflichtet
    -0.70
    uran
    -0.68
    YES
    -0.68
     porridge
    -0.68
    POSITIVE LOGITS
     reson
    0.93
    IDX
    0.91
    ORA
    0.84
    eny
    0.82
    revert
    0.82
    理由
    0.79
     Riva
    0.79
    mschrijving
    0.78
    Pró
    0.78
    Purchased
    0.77
    Activations Density 0.000%

    No Known Activations