© 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. 13362
    Prev
    Next
    INDEX
    Explanations

    and conjunction

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

    The neuron detects numeric tokens (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_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
     vuelto
    -1.05
    埝
    -1.02
     lã
    -1.01
     természetes
    -0.98
     Conſ
    -0.98
    zeugt
    -0.98
    xvii
    -0.98
    小さ
    -0.98
    垸
    -0.98
     sandalias
    -0.97
    POSITIVE LOGITS
     its
    1.59
     how
    1.33
     provide
    1.32
     surroundings
    1.15
     while
    0.99
     related
    0.98
     uses
    0.98
     what
    0.97
     particularly
    0.95
     have
    0.93
    Activations Density 0.089%

    No Known Activations