© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34003
    Prev
    Next
    INDEX
    Explanations

    counting sides and directions

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

    The neuron is detecting numeric tokens (literal 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_22/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
     beiden
    -1.05
    eniu
    -1.00
    Ḳ
    -0.96
     สอง
    -0.96
    urnya
    -0.95
    owaniu
    -0.94
    typal
    -0.94
    וֹ
    -0.94
    vikling
    -0.91
     nutrición
    -0.91
    POSITIVE LOGITS
     four
    1.37
     all
    1.20
     croche
    1.02
     five
    1.00
    四个
    0.99
     three
    0.99
     chré
    0.98
     keempat
    0.96
    usura
    0.95
     six
    0.90
    Activations Density 0.059%

    No Known Activations