© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    code blocks and configuration

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

    This neuron activates on tokens that are numeric sequences (i.e. tokens composed primarily of digits).

    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
    a
    -1.06
    I
    -1.02
    S
    -1.02
    g
    -1.01
    A
    -1.00
    d
    -1.00
    ..
    -0.99
    -
    -0.98
    --
    -0.98
    e
    -0.98
    POSITIVE LOGITS
    Kontra
    1.06
    Grafik
    1.05
    Kto
    1.03
    Makan
    1.03
    Szer
    1.00
    adakan
    0.98
    Karakter
    0.98
    嘁
    0.97
     способствует
    0.97
    cierre
    0.97
    Activations Density 0.093%

    No Known Activations