© 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. 34-GEMMASCOPE-RES-131K
    7. 103648
    Prev
    Next
    INDEX
    Explanations

    Go Authors

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

    The neuron activates on numeric tokens (i.e. sequences of digits or numeric literals).

    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
     meticulous
    -1.13
     meticulously
    -1.12
     fully
    -0.90
     unwavering
    -0.89
     supremely
    -0.87
     even
    -0.84
    設施
    -0.83
    órias
    -0.83
    ات
    -0.81
     by
    -0.81
    POSITIVE LOGITS
    simply
    1.06
     MATTERS
    1.05
    usually
    1.02
    forty
    1.01
    keep
    1.00
    commonly
    1.00
    めちゃ
    0.99
     farmacé
    0.97
    {}
    0.95
    probably
    0.94
    Activations Density 0.003%

    No Known Activations