© 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. 34-GEMMASCOPE-RES-131K
    4. 76039
    Prev
    Next
    INDEX
    Explanations

    job news or connecticut surveys

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

    The neuron is detecting numeric literals (especially CSS measurement values and related tokens) within code blocks.

    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
    Nuevo
    -0.80
    strokes
    -0.79
    Font
    -0.74
    ıyoruz
    -0.73
     поси
    -0.73
     font
    -0.73
     Sloveniji
    -0.72
     fuite
    -0.71
    Convergence
    -0.71
     Fon
    -0.70
    POSITIVE LOGITS
     same
    0.84
    oreo
    0.80
     diffraction
    0.79
     animasi
    0.78
     Anima
    0.78
    ㄗ
    0.77
    ℣
    0.77
    Enciclopedia
    0.77
    Anima
    0.77
    からない
    0.77
    Activations Density 0.024%

    No Known Activations