© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128877
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for numeric tokens (numbers) in the text.

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

    introducing categories

    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
     “…
    -1.45
     mendatang
    -1.39
     bArr
    -1.31
     bleef
    -1.31
     maakte
    -1.28
    шени
    -1.20
    нём
    -1.19
     все
    -1.19
     “
    -1.16
    🏅
    -1.16
    POSITIVE LOGITS
     things
    2.13
     maybe
    1.97
     stuff
    1.90
     thing
    1.82
     kind
    1.77
     vielleicht
    1.66
    
    1.63
     kinda
    1.62
     [
    1.61
    或者是
    1.53
    Activations Density 0.009%

    No Known Activations