© 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. 35250
    Prev
    Next
    INDEX
    Explanations

    links and citations

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

    The neuron fires on standalone numerical tokens—i.e. it detects numbers (digits and numeric values) 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
    sions
    -0.96
    chik
    -0.89
    ølge
    -0.85
     tē
    -0.81
     ``
    -0.79
     re
    -0.79
    lesia
    -0.78
     this
    -0.77
     sā
    -0.74
    sive
    -0.73
    POSITIVE LOGITS
     État
    0.90
    pewa
    0.88
    ᚦ
    0.82
     déliv
    0.81
     prét
    0.81
     別注
    0.81
    ♤
    0.81
    ughter
    0.78
    refu
    0.78
    kredit
    0.78
    Activations Density 0.591%

    No Known Activations