© 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. 32884
    Prev
    Next
    INDEX
    Explanations

    specialist titles

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

    The neuron fires on numeric tokens (numbers and numeric literals) in the text.

    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
     «
    -1.05
    Obrigada
    -1.04
    Abraços
    -1.04
    This
    -1.00
    érer
    -1.00
    Why
    -0.98
    Abraço
    -0.98
    ''
    -0.98
    Até
    -0.98
    With
    -0.95
    POSITIVE LOGITS
     fiscales
    1.30
     civiles
    1.30
     cổng
    1.13
     kvinnor
    1.11
     vänner
    1.09
     haine
    1.03
    ̫
    1.02
     neuve
    1.02
     pouce
    1.02
     juſ
    1.01
    Activations Density 0.031%

    No Known Activations