© 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. 127959
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily identifies numeric tokens (i.e. any numbers or number‐containing strings) in the text.

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

    Michael Dwyer

    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
     svoje
    -1.17
     my
    -1.08
     verksamhet
    -1.07
    ”？
    -1.07
    Sqft
    -1.05
    trump
    -1.02
    belts
    -1.02
     limpia
    -1.00
     desnuda
    -1.00
    君は
    -0.99
    POSITIVE LOGITS
     they
    1.44
    ञ
    1.05
     we
    1.01
    viève
    1.00
     their
    0.99
     их
    0.97
     verificare
    0.96
     chúng
    0.95
    平日
    0.95
    终于
    0.91
    Activations Density 0.002%

    No Known Activations