© 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. 34-GEMMASCOPE-RES-131K
    7. 34560
    Prev
    Next
    INDEX
    Explanations

    get all

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

    The neuron fires on occurrences of “get” (in any case) – especially when used as an API or method name.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Дата
    -1.04
    /">
    -1.04
    culaire
    -0.91
     Saltar
    -0.90
     VALUES
    -0.90
    -',
    -0.89
    谙
    -0.88
    uuml
    -0.88
    BagConstraints
    -0.87
     incluso
    -0.87
    POSITIVE LOGITS
     all
    2.53
    所有
    1.64
    all
    1.55
    所有的
    1.55
     available
    1.55
     всички
    1.48
     semua
    1.47
     wszystkich
    1.44
     tutte
    1.41
     tất
    1.39
    Activations Density 0.021%

    No Known Activations