© 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. 63492
    Prev
    Next
    INDEX
    Explanations

    numbers followed by time

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

    The neuron fires on numeric tokens—i.e. it detects numbers (years, counts, scores, and other multi‐digit numerals) 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
     or
    -1.18
    rafa
    -1.02
     dingen
    -1.00
    gangss
    -0.99
    Ƿ
    -0.99
     leggen
    -0.98
     ongeveer
    -0.98
     \\
    -0.98
     ym
    -0.98
     krijgt
    -0.96
    POSITIVE LOGITS
     dozen
    1.02
    hundred
    0.99
     наверное
    0.98
     Agencia
    0.91
     Certainly
    0.88
     since
    0.88
     of
    0.88
     different
    0.88
     возможностей
    0.87
     ago
    0.86
    Activations Density 0.128%

    No Known Activations