© 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. 22-GEMMASCOPE-RES-131K
    7. 27943
    Prev
    Next
    INDEX
    Explanations

    newest, latest, recent, last

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

    The neuron fires on numeric tokens (i.e. standalone numbers or digit sequences) 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_22/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
     across
    -0.95
     around
    -0.89
     for
    -0.89
     suggestion
    -0.84
     suggestions
    -0.84
     common
    -0.83
     fore
    -0.81
     far
    -0.81
     even
    -0.81
     here
    -0.80
    POSITIVE LOGITS
     newest
    1.52
     new
    1.47
     recent
    1.45
    ใหม่
    1.39
    の新
    1.36
    新增
    1.34
     جدید
    1.33
     latest
    1.29
    新
    1.23
    newest
    1.20
    Activations Density 0.021%

    No Known Activations