© 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. 77632
    Prev
    Next
    INDEX
    Explanations

    mathematical notation `$\leq`

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

    This neuron detects numeric tokens (digits and numeric literals) in code and 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
     pluie
    -0.94
     utbild
    -0.70
    リット
    -0.69
    ạt
    -0.69
     restorative
    -0.69
    Cassie
    -0.68
    Jax
    -0.67
    FromString
    -0.67
    Teaser
    -0.66
     chase
    -0.66
    POSITIVE LOGITS
    诗
    0.72
     volume
    0.72
     dùng
    0.69
    VOLUME
    0.68
    regar
    0.67
     Reporters
    0.65
    Reports
    0.65
    vok
    0.65
     resource
    0.64
     concluded
    0.63
    Activations Density 0.056%

    No Known Activations