© 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. 10-GEMMASCOPE-RES-131K
    7. 87103
    Prev
    Next
    INDEX
    Explanations

    numbers with percentage or +/-

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

    The neuron detects numeric statistical or measurement values (e.g. p‐values, confidence intervals, means ± SD, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     veramente
    -1.79
    iſ
    -1.69
     davvero
    -1.68
     déplacer
    -1.58
    ఽ
    -1.54
    茈
    -1.51
    皈
    -1.50
     destinés
    -1.44
    
    -1.41
    ᱸ
    -1.40
    POSITIVE LOGITS
     in
    2.20
     during
    2.09
     when
    2.06
     within
    1.95
     each
    1.93
     first
    1.84
     because
    1.77
     and
    1.76
     intricate
    1.75
     over
    1.73
    Activations Density 0.152%

    No Known Activations