© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92369
    Prev
    Next
    INDEX
    Explanations

    coordinates in mathematical notation

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

    The neuron selectively fires on numeric tokens (integer or coordinate values) in the mathematical 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
     others
    -1.33
     then
    -0.99
    Others
    -0.96
     of
    -0.92
     continued
    -0.90
    лова
    -0.89
     naszego
    -0.88
    を
    -0.86
     with
    -0.83
     also
    -0.83
    POSITIVE LOGITS
     _,
    1.31
    ?,?,
    1.17
     '.',
    1.13
     ',',
    1.05
     ?,
    1.03
     baloncesto
    0.94
    courtesy
    0.94
    ubri
    0.94
    tagHelper
    0.94
    ניה
    0.94
    Activations Density 0.032%

    No Known Activations