© 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. 33024
    Prev
    Next
    INDEX
    Explanations

    offers, scholarships, jobs, details

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

    The neuron strongly activates on standalone numbers (and short alphanumeric/ordinal tokens built from digits), i.e. numeric values like prices, dates, scores, counts, etc.

    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
     três
    -1.03
    aporte
    -1.01
    tappe
    -1.00
    Laser
    -0.97
     Ensino
    -0.97
    新冠
    -0.96
    criptions
    -0.96
    obatan
    -0.96
    нін
    -0.95
    "—
    -0.94
    POSITIVE LOGITS
    、【
    1.08
     /
    1.05
     detailed
    1.04
    :-
    1.02
    这一幕
    1.02
    さんも
    0.98
    atória
    0.97
     |
    0.96
     aperçu
    0.96
     ||
    0.96
    Activations Density 0.150%

    No Known Activations