© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75122
    Prev
    Next
    INDEX
    Explanations

    assigning false or null

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

    This neuron fires on literal default values or initializers in code (e.g. strings, numbers, nulls) that are assigned to variables or parameters.

    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
     only
    -0.91
     Washington
    -0.82
    clav
    -0.81
    XCTAssert
    -0.81
    pone
    -0.80
    pu
    -0.76
     Massachusetts
    -0.76
    Ab
    -0.75
    ysan
    -0.74
     ||
    -0.73
    POSITIVE LOGITS
     plastica
    0.91
    assemblée
    0.88
    decide
    0.87
     նաև
    0.87
    🅳
    0.86
    新しい
    0.85
     koncer
    0.84
    Déc
    0.83
    Fragen
    0.83
    ᾧ
    0.82
    Activations Density 0.024%

    No Known Activations