© 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. 22-GEMMASCOPE-RES-131K
    7. 128455
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (digits, years, counts, measurements, etc.) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    years and names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     sibi
    -0.96
     derer
    -0.86
     mab
    -0.86
     теперь
    -0.85
    水槽
    -0.84
     lern
    -0.82
     sejak
    -0.82
     arbeit
    -0.81
    assum
    -0.81
     misst
    -0.80
    POSITIVE LOGITS
    Эти
    1.02
    みよう
    0.99
    leicht
    0.97
    obod
    0.97
     зару
    0.95
    ญี่ป
    0.92
     einzigartigen
    0.92
    leute
    0.92
    sə
    0.91
    dı
    0.90
    Activations Density 0.011%

    No Known Activations