© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127984
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on standalone numeric tokens (i.e. integer quantities). It flags occurrences of numbers.

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

    with

    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
     or
    -1.28
    👁
    -1.16
     it
    -1.15
     you
    -1.10
    SSI
    -1.09
    キュリティ
    -1.09
     obyvateľov
    -1.05
     RemoteException
    -1.05
    场比赛
    -1.04
    ėjimas
    -1.03
    POSITIVE LOGITS
     a
    2.05
     something
    1.61
     Japão
    1.47
     enough
    1.34
     more
    1.34
     another
    1.29
     encontro
    1.29
     Tropfen
    1.27
     banheiro
    1.25
     anúncio
    1.23
    Activations Density 0.052%

    No Known Activations