© 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. 38212
    Prev
    Next
    INDEX
    Explanations

    matrix and array notation

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

    This neuron detects numeric literal tokens (especially “0” and other small integers) in equations or code snippets.

    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
    C
    -1.20
    N
    -1.10
    R
    -1.09
    in
    -1.05
    d
    -1.05
    A
    -1.04
    P
    -1.04
    G
    -0.99
    I
    -0.99
    F
    -0.98
    POSITIVE LOGITS
    struzioni
    1.23
     atau
    1.13
    siąż
    1.02
    Reina
    1.02
    Essen
    0.99
    Recher
    0.99
    uarts
    0.99
    Leopard
    0.98
     tega
    0.97
    Vulkan
    0.95
    Activations Density 0.014%

    No Known Activations