© 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. 116976
    Prev
    Next
    INDEX
    Explanations

    Saskatchewan CA signal

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

    The neuron fires on standalone numeric tokens (digits or digit‐containing codes) that appear as quantities or identifiers—e.g. element counts in chemical formulas and state/postal codes.

    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
     cord
    -0.79
    compatible
    -0.75
    pasti
    -0.70
     بارداری
    -0.69
    }{||
    -0.69
    δου
    -0.68
    Cord
    -0.67
    atst
    -0.67
     elliptic
    -0.66
    ்கள
    -0.66
    POSITIVE LOGITS
     Insol
    0.78
     GBA
    0.67
    berger
    0.66
     gh
    0.66
     diện
    0.65
     Trotsky
    0.65
     FTX
    0.65
    cS
    0.64
     getS
    0.64
     dk
    0.64
    Activations Density 0.060%

    No Known Activations