© 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. 26285
    Prev
    Next
    INDEX
    Explanations

    two or three items

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

    The neuron activates on numeric tokens and numerical expressions (e.g., numbers, decimals) in 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
     основном
    -1.23
    phosa
    -1.03
    mainly
    -1.03
    namiento
    -1.01
    hrer
    -1.01
    primarily
    -1.00
     Certaines
    -0.98
     cucharadas
    -0.97
    requipa
    -0.97
    हां
    -0.97
    POSITIVE LOGITS
     hypothetical
    1.38
     his
    1.27
     would
    1.26
     scenario
    1.20
     same
    1.19
     may
    1.16
    すすめ
    1.13
     a
    1.11
     two
    1.06
     magari
    1.02
    Activations Density 0.058%

    No Known Activations