© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14762
    Prev
    Next
    INDEX
    Explanations

    variables and dummies

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

    The neuron primarily activates on numeric tokens (i.e. numbers) in the 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_22/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
    資源
    -0.96
    চ্
    -0.95
     设置
    -0.94
    ：……
    -0.92
    Zutaten
    -0.91
     hidupnya
    -0.86
    香味
    -0.85
    分布
    -0.85
    Testo
    -0.85
    Punj
    -0.84
    POSITIVE LOGITS
     мә
    1.08
     variables
    1.06
    jstor
    0.99
    ännande
    0.98
     وأن
    0.96
    ᄀ
    0.94
    zeria
    0.91
    وأضاف
    0.90
     Nick
    0.88
     into
    0.88
    Activations Density 0.067%

    No Known Activations