© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    generated by class-dump

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

    The neuron activates on standalone numeric tokens (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_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
     wth
    -1.84
     waa
    -1.66
     alamu
    -1.66
    ’
    -1.66
     Maak
    -1.63
     Græ
    -1.63
     Jé
    -1.60
    渽
    -1.59
    除此之外
    -1.59
     daire
    -1.59
    POSITIVE LOGITS
    ↵↵
    1.83
    us
    1.83
    держан
    1.75
    从
    1.73
     {
    1.67
    开始
    1.62
    to
    1.62
    <blockquote>
    1.60
    ный
    1.60
    ные
    1.59
    Activations Density 0.057%

    No Known Activations