© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15552
    Prev
    Next
    INDEX
    Explanations

    programming code context

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

    The neuron fires on tokens that contain digits—i.e. numeric literals or version/identifier 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_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
    ！　
    -0.92
    reur
    -0.89
     diaspora
    -0.88
    otesi
    -0.87
     następujące
    -0.86
    ？　
    -0.86
    ajinan
    -0.84
    ！”
    -0.84
     Schuld
    -0.82
     graduated
    -0.82
    POSITIVE LOGITS
     counterpart
    1.01
     counterparts
    0.86
    🥃
    0.84
    🍆
    0.81
    克力
    0.79
    compare
    0.77
    那边
    0.76
    aremos
    0.74
    ológ
    0.74
    けれ
    0.74
    Activations Density 0.031%

    No Known Activations