© 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. 10-GEMMASCOPE-RES-131K
    7. 15307
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by mathematical or structural text

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

    The neuron activates on standalone numeric tokens (i.e. any numbers appearing 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_10/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
     sebagainya
    -2.31
     sembler
    -1.81
    chtigkeit
    -1.80
     kleinen
    -1.72
     verrou
    -1.67
    ௅
    -1.67
    诬
    -1.65
     kurzem
    -1.65
    راسیون
    -1.60
    zegovina
    -1.59
    POSITIVE LOGITS
    this
    1.99
     sentire
    1.88
    ers
    1.88
    n
    1.80
    to
    1.77
    c
    1.70
     Its
    1.67
     liberi
    1.64
     notare
    1.64
     网站
    1.64
    Activations Density 0.011%

    No Known Activations