© 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. 130875
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to standalone numeric tokens (i.e. numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    job titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     estrena
    -1.56
     Agrega
    -1.41
     volverá
    -1.36
    licante
    -1.35
     ilustracji
    -1.34
     nació
    -1.30
     レスト
    -1.28
     個室
    -1.28
     brengt
    -1.26
    뽐
    -1.26
    POSITIVE LOGITS
     D
    1.13
     very
    1.11
     small
    1.10
     food
    1.10
     F
    1.09
     low
    1.09
     a
    1.06
     not
    1.05
     medical
    1.04
    .
    1.03
    Activations Density 0.020%

    No Known Activations