© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38530
    Prev
    Next
    INDEX
    Explanations

    enum types and states

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

    This neuron fires on uppercase enum or constant identifiers (e.g. enum members or `case` labels).

    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
     memudahkan
    -1.19
     and
    -1.17
     mempengaruhi
    -1.05
     тоже
    -1.02
    angkap
    -1.02
     berguna
    -1.02
     虾
    -1.00
    fänger
    -0.99
    جاب
    -0.99
     comuniques
    -0.99
    POSITIVE LOGITS
     heridas
    1.09
    了一声
    1.08
    *}{
    1.06
     voire
    1.06
     autre
    1.06
    logiques
    1.02
     limitaciones
    1.02
     vacío
    1.02
    حتی
    1.00
     ellos
    0.99
    Activations Density 0.002%

    No Known Activations