© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    width values

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

    This neuron detects numeric literals (sequences of digits) in code or markup.

    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
    showthread
    -1.00
     sólo
    -0.93
     only
    -0.90
    getHeight
    -0.88
     at
    -0.85
     says
    -0.83
     getHeight
    -0.80
     September
    -0.79
    Despite
    -0.77
    nextProps
    -0.77
    POSITIVE LOGITS
     Width
    1.19
    width
    1.09
     width
    1.08
     widths
    0.99
     screen
    0.94
     WIDTH
    0.93
    WIDTH
    0.92
    蠃
    0.92
     обеспе
    0.91
     организации
    0.90
    Activations Density 0.014%

    No Known Activations