© 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. 12028
    Prev
    Next
    INDEX
    Explanations

    Android attribute names and UI elements

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

    This neuron activates on tokens that include numeric digits (e.g. version numbers, dimensions, or resource names containing numbers).

    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
    žių
    -0.90
     and
    -0.90
    xyl
    -0.89
    嚴重
    -0.88
    tionally
    -0.88
     Gewebe
    -0.85
    panes
    -0.85
    謬
    -0.85
    付いて
    -0.83
    燁
    -0.83
    POSITIVE LOGITS
    Zutaten
    1.09
    rored
    1.04
    Rohy
    0.97
    Einen
    0.95
    إن
    0.92
    arska
    0.91
     bättre
    0.91
    Татьяна
    0.90
    Keine
    0.90
    Material
    0.89
    Activations Density 0.003%

    No Known Activations