© 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. 129044
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on standalone numeric tokens (i.e. numbers in the text).

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

    section headers and code comments

    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
     Even
    -1.36
     This
    -1.29
     this
    -1.23
    this
    -1.22
     even
    -1.20
    This
    -1.18
     M
    -1.16
     will
    -1.16
     In
    -1.15
    '
    -1.14
    POSITIVE LOGITS
     choroby
    1.41
    包括
    1.35
    
    1.30
     its
    1.29
    tarta
    1.27
     puentes
    1.27
     diferite
    1.26
     reemplazo
    1.24
     estabiliz
    1.23
     plantillas
    1.22
    Activations Density 0.003%

    No Known Activations