© 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. 14080
    Prev
    Next
    INDEX
    Explanations

    CIRC

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

    The neuron activates on numeric tokens (both integers and decimals), i.e. it finds numbers 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
    Declar
    -0.80
    достатки
    -0.78
    炊き
    -0.77
     سیاه
    -0.74
    Algeria
    -0.73
    %#
    -0.73
     Eğ
    -0.73
    vall
    -0.72
     Patrick
    -0.72
     Sc
    -0.71
    POSITIVE LOGITS
     (!__
    0.95
     }}(\
    0.86
     Bezir
    0.85
     awesome
    0.85
    ﻮ
    0.84
     invá
    0.82
    North
    0.82
     practices
    0.81
     Grâce
    0.81
     local
    0.79
    Activations Density 0.061%

    No Known Activations