© 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. 16316
    Prev
    Next
    INDEX
    Explanations

    groups and demographics

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

    The neuron is strongly activated by numeric tokens (digits or quantities) 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
     nonché
    -1.14
    などを
    -1.08
     eigene
    -1.04
    a
    -1.02
     seno
    -0.97
     do
    -0.94
     are
    -0.94
     '
    -0.93
    がある
    -0.93
    震撼
    -0.92
    POSITIVE LOGITS
    mizuno
    1.31
     huellas
    1.30
    płat
    1.23
    bliž
    1.22
     ReactDOM
    1.20
    namientos
    1.17
    př
    1.17
    June
    1.16
     trám
    1.14
    useNewUrlParser
    1.13
    Activations Density 0.050%

    No Known Activations