© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13623
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    The neuron primarily responds to four‐digit numeric tokens (especially years and other document identifiers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     that
    -1.41
     Gruppe
    -1.13
     and
    -1.13
     should
    -1.09
     departament
    -1.07
     would
    -1.04
     but
    -1.02
    thday
    -0.99
     давно
    -0.97
     statistik
    -0.96
    POSITIVE LOGITS
    눌
    1.18
    有点
    1.18
    porque
    1.17
    Kde
    1.15
    uristic
    1.13
    smh
    1.11
    lysm
    1.11
    icône
    1.11
    asca
    1.08
    banez
    1.08
    Activations Density 0.011%

    No Known Activations