© 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. 66280
    Prev
    Next
    INDEX
    Explanations

    AUTOINCREMENT or AUTO_INCREMENT

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

    The neuron activates on numeric tokens—i.e. digit sequences representing numbers.

    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
    PageSize
    -0.79
     ederim
    -0.74
     organized
    -0.71
     ними
    -0.71
    ⅹ
    -0.70
     渡
    -0.70
     ekonomi
    -0.69
     phí
    -0.69
     prioritizing
    -0.69
    readlines
    -0.69
    POSITIVE LOGITS
     sequence
    2.11
     sequences
    1.95
     Sequence
    1.84
    sequence
    1.80
    Sequence
    1.77
     seq
    1.74
    seq
    1.62
     Sequences
    1.55
    Seq
    1.55
    sequences
    1.55
    Activations Density 0.017%

    No Known Activations