© 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. 80027
    Prev
    Next
    INDEX
    Explanations

    system namespaces

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

    The neuron fires on standalone integer tokens in code (numeric literals).

    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
     usual
    -1.12
     to
    -1.11
    prits
    -1.02
    了不少
    -0.99
     mascarpone
    -0.97
    patra
    -0.96
    Exeunt
    -0.95
    );
    -0.95
     even
    -0.94
     overall
    -0.94
    POSITIVE LOGITS
     mètre
    1.04
     réservoir
    1.03
     gouvernements
    1.02
     coussin
    1.01
     œufs
    1.01
    ●●
    0.98
    wnątrz
    0.97
    bkz
    0.96
    inematic
    0.96
    Ингредиенты
    0.96
    Activations Density 0.007%

    No Known Activations