© 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. 67584
    Prev
    Next
    INDEX
    Explanations

    Eureka, Shipping, Emma

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

    The neuron fires on comma tokens (particularly in license‐ and comment‐style 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_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
     montón
    -1.24
     Drž
    -1.18
    なのかな
    -1.14
     Czę
    -1.12
     its
    -1.12
     évé
    -1.10
     soyez
    -1.10
    milan
    -1.09
     moletom
    -1.06
     sabias
    -1.05
    POSITIVE LOGITS
     främ
    1.05
     непосредственно
    1.01
     indigent
    0.94
    ēc
    0.93
     interceptor
    0.93
     EHR
    0.92
     ESL
    0.90
    if
    0.90
    le
    0.90
    ha
    0.90
    Activations Density 0.000%

    No Known Activations