© 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. 33314
    Prev
    Next
    INDEX
    Explanations

    Changan Automobile

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

    The neuron detects standalone numeric tokens, such as page numbers, identifiers, years, and other numerical references.

    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
    Ông
    -0.78
    Treas
    -0.76
    婪
    -0.75
    Dres
    -0.75
     methane
    -0.75
    cartItem
    -0.73
    Scary
    -0.73
     նա
    -0.73
    ENGLISH
    -0.72
    Cozy
    -0.72
    POSITIVE LOGITS
     necessidade
    0.86
    Ո
    0.81
    Anderson
    0.80
     vort
    0.80
     necesidad
    0.79
    キュー
    0.77
    と言
    0.76
     nephews
    0.76
     単
    0.75
     ligação
    0.74
    Activations Density 0.001%

    No Known Activations