© 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. 25995
    Prev
    Next
    INDEX
    Explanations

    New Hampshire, PEG precipitates, protocol NS

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

    The neuron activates on numeric tokens—both integers and decimals—i.e. it’s detecting numbers and numeric measurements 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
     to
    -0.92
     on
    -0.92
    run
    -0.85
     extraordin
    -0.81
    simple
    -0.80
    AutoField
    -0.79
    日が
    -0.78
    mice
    -0.77
     άλ
    -0.77
    real
    -0.77
    POSITIVE LOGITS
     tromper
    0.90
     компьютера
    0.88
     stroom
    0.86
    harap
    0.85
     aviones
    0.85
     temperatuur
    0.84
     ibland
    0.82
    Liu
    0.82
    Guo
    0.82
     giapp
    0.81
    Activations Density 0.001%

    No Known Activations