© 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. 10-GEMMASCOPE-RES-131K
    7. 86359
    Prev
    Next
    INDEX
    Explanations

    null or annotations

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

    This neuron activates on occurrences of the term “Nullable” (e.g. annotation imports or XML tags).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Atención
    -1.73
     But
    -1.70
     δεν
    -1.68
     แต่
    -1.68
     не
    -1.65
     Where
    -1.65
    CIÓN
    -1.60
     {
    -1.59
     officielle
    -1.55
    емъ
    -1.51
    POSITIVE LOGITS
    蔟
    1.54
    盦
    1.51
     currently
    1.48
    鸲
    1.47
    亊
    1.44
    са
    1.43
     despacho
    1.41
    tiéndose
    1.40
    income
    1.38
    蕺
    1.38
    Activations Density 0.003%

    No Known Activations