© 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. 73583
    Prev
    Next
    INDEX
    Explanations

    numbers in dates

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

    The neuron predominantly activates on numeric tokens—especially digits and dots used in decimals or version‐style number sequences.

    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
     if
    -1.70
     to
    -1.66
     should
    -1.64
     \
    -1.58
     would
    -1.41
    mathrm
    -1.41
    と思ったら
    -1.41
     has
    -1.39
     {
    -1.38
     when
    -1.35
    POSITIVE LOGITS
    紇
    1.66
    曏
    1.59
    neté
    1.45
     blessures
    1.41
     dalších
    1.41
    琤
    1.41
     των
    1.40
     honn
    1.38
    jenige
    1.38
    ⣞
    1.38
    Activations Density 0.091%

    No Known Activations