© 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. 42503
    Prev
    Next
    INDEX
    Explanations

    court documents and software

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

    The neuron strongly activates on standalone numeric tokens (integers or decimals), i.e. it detects numbers 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
     '
    -2.14
    -
    -1.89
    '
    -1.88
     Then
    -1.85
     Always
    -1.77
     Including
    -1.77
     The
    -1.76
     same
    -1.73
     is
    -1.72
     "
    -1.69
    POSITIVE LOGITS
    ですが
    1.93
    我不
    1.91
    开始
    1.89
    １
    1.80
    ㈯
    1.80
    !»
    1.78
    ３
    1.78
    뚠
    1.77
    ‼
    1.77
    ?»
    1.76
    Activations Density 0.009%

    No Known Activations