© 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. 22-GEMMASCOPE-RES-131K
    7. 104542
    Prev
    Next
    INDEX
    Explanations

    collaborates with systems

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

    The neuron activates on tokens containing digits or numeric characters (e.g. reference IDs, statistical numbers, decimal values).

    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
     other
    -0.96
     conformidad
    -0.93
    还是要
    -0.92
    厢
    -0.92
     consentimento
    -0.92
    还得
    -0.92
     Tieren
    -0.91
     actuels
    -0.91
     heuti
    -0.91
    辆
    -0.91
    POSITIVE LOGITS
    ensdag
    1.16
    Nép
    1.13
    包含
    1.08
    Probably
    1.05
    ÕES
    1.04
     terlaris
    1.03
     plik
    1.01
     either
    0.99
    ܠ
    0.97
    Getting
    0.95
    Activations Density 0.021%

    No Known Activations