© 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. 74986
    Prev
    Next
    INDEX
    Explanations

    starting or initial values

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

    The neuron fires on numeric literals (numbers) in code or technical text.

    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
     before
    -0.88
     during
    -0.86
    それとも
    -0.82
     within
    -0.82
     около
    -0.81
    🚤
    -0.79
    Before
    -0.76
    formation
    -0.75
    currentTime
    -0.74
    elseif
    -0.74
    POSITIVE LOGITS
     starting
    1.62
     시작
    1.37
    starting
    1.31
    起始
    1.30
    estart
    1.23
    เริ่ม
    1.13
    Starting
    1.11
     empezar
    1.08
    STARTING
    1.08
     empez
    1.04
    Activations Density 0.022%

    No Known Activations