© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39743
    Prev
    Next
    INDEX
    Explanations

    after or subsequent

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

    The neuron strongly activates on numeric tokens (sequences of digits), i.e. it detects numbers.

    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
    rell
    -0.82
     ecran
    -0.75
     简
    -0.75
     régi
    -0.75
    isé
    -0.73
    sihkan
    -0.73
     wynika
    -0.73
     Prze
    -0.73
     Kläger
    -0.72
    <0xE2>
    -0.71
    POSITIVE LOGITS
     baada
    0.97
     after
    0.95
    之後
    0.91
     بعد
    0.86
     después
    0.85
    鵝
    0.84
    之后的
    0.81
    後に
    0.80
    之后
    0.80
     setelah
    0.79
    Activations Density 0.015%

    No Known Activations