© 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. 87001
    Prev
    Next
    INDEX
    Explanations

    powers and roots

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

    The neuron is detecting numeric tokens (digits and multi‐digit 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
     second
    -0.88
     quadratic
    -0.81
    🥈
    -0.80
    二级
    -0.77
     kaksi
    -0.77
     دوم
    -0.75
    Second
    -0.75
    保護
    -0.74
     square
    -0.74
     Zwei
    -0.73
    POSITIVE LOGITS
     cubed
    2.13
     cube
    2.08
     cubic
    1.94
     fourth
    1.85
     third
    1.83
     Cube
    1.75
    cubic
    1.70
    cube
    1.68
    Cubic
    1.66
     Cubic
    1.65
    Activations Density 0.116%

    No Known Activations