© 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. 103383
    Prev
    Next
    INDEX
    Explanations

    php and programming libraries

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

    The neuron is primarily detecting numeric literals (multi‐digit numbers) in code or 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_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
     that
    -1.08
     not
    -1.06
     last
    -0.94
     but
    -0.93
     both
    -0.93
     autoestima
    -0.91
     continuó
    -0.87
     on
    -0.86
     because
    -0.85
     with
    -0.85
    POSITIVE LOGITS
    蓠
    1.09
     ?',
    1.05
    ;</
    0.97
    ()">
    0.96
     marseille
    0.95
    了一声
    0.95
    фов
    0.95
    outWeight
    0.94
    ModelAttribute
    0.94
    逦
    0.93
    Activations Density 0.038%

    No Known Activations