© 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. 34-GEMMASCOPE-RES-131K
    7. 63841
    Prev
    Next
    INDEX
    Explanations

    code, legal, and multilingual text

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

    The neuron fires on numeric tokens (any standalone numbers or 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_34/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
    льта
    -0.71
     originality
    -0.70
    rato
    -0.65
    udan
    -0.65
     hình
    -0.65
    itonitis
    -0.65
    ffield
    -0.64
     Makefile
    -0.64
     kingdoms
    -0.63
    kkelen
    -0.62
    POSITIVE LOGITS
    quoted
    0.75
     przy
    0.72
    backed
    0.70
    BRIAN
    0.68
    purple
    0.68
    ASED
    0.67
     Conseils
    0.67
    طلاق
    0.67
    ogue
    0.66
     və
    0.66
    Activations Density 0.040%

    No Known Activations