© 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. 27242
    Prev
    Next
    INDEX
    Explanations

    Q: or question

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

    The neuron consistently activates on numeric tokens—i.e. sequences of digits or numbers within 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
     at
    -1.42
     respectivamente
    -1.07
     anstatt
    -1.01
     information
    -1.00
     attaining
    -1.00
     will
    -1.00
    setupUi
    -0.99
    licants
    -0.98
    detek
    -0.98
    лыша
    -0.98
    POSITIVE LOGITS
     ſever
    1.38
     Reſ
    1.21
     السياس
    1.21
    казать
    1.14
     ſmall
    1.13
    神
    1.12
    leggio
    1.11
     protéines
    1.11
     alho
    1.08
     ſol
    1.06
    Activations Density 0.003%

    No Known Activations