© 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. 64553
    Prev
    Next
    INDEX
    Explanations

    ordering mathematical fractions and sequences

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

    The neuron activates on numeric tokens (integers or decimals), i.e. it detects the presence of numbers.

    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
    courses
    -0.96
     numa
    -0.92
     ldc
    -0.92
    lccn
    -0.92
    formatie
    -0.92
     msg
    -0.91
    middels
    -0.90
     comunidade
    -0.88
     می‌کنند
    -0.86
    VideoView
    -0.85
    POSITIVE LOGITS
    <bos>
    1.09
    asına
    1.05
     Organizador
    1.03
     Estructura
    1.03
     Segurança
    0.97
     alemão
    0.94
    anty
    0.94
     Songtext
    0.94
     Reihenfolge
    0.93
     لهذه
    0.93
    Activations Density 0.007%

    No Known Activations