© 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. 90040
    Prev
    Next
    INDEX
    Explanations

    explaining or hoping

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

    The neuron predominantly activates on numeric tokens or standalone numbers (e.g., counts, measurements, years, and other digit sequences).

    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
    khó
    -0.91
     као
    -0.73
    éez
    -0.72
    Hiện
    -0.71
    <td>
    -0.71
    Será
    -0.71
    Ngày
    -0.70
    Được
    -0.69
    жного
    -0.69
     with
    -0.68
    POSITIVE LOGITS
    Explanation
    3.13
     Explanation
    2.89
     explanation
    2.50
     hope
    1.95
    explanation
    1.85
    hope
    1.63
    Hope
    1.63
     answer
    1.60
     HOPE
    1.59
     EXPLANATION
    1.57
    Activations Density 0.039%

    No Known Activations