© 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. 105424
    Prev
    Next
    INDEX
    Explanations

    diverse articles, languages, and punctuation

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

    The neuron activates on decimal-number tokens (floating-point statistics, percentages, or effect-size values) 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_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
    )
    -1.84
     to
    -1.77
    ...
    -1.70
    =
    -1.62
    '''
    -1.62
     only
    -1.58
     ....
    -1.52
     «
    -1.50
    j
    -1.49
    »
    -1.49
    POSITIVE LOGITS
    ఌ
    1.69
     batteria
    1.49
     Lengkap
    1.45
    Olvid
    1.43
    يطاليا
    1.42
    roughts
    1.41
     they
    1.41
    quién
    1.37
    problemas
    1.35
     também
    1.34
    Activations Density 0.533%

    No Known Activations