© 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. 130386
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to standalone numeric tokens (digits or numeric symbols) such as years, counts, or cron-style wildcards.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code, data, and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Universidades
    -1.14
     máme
    -1.04
     índice
    -0.99
    methode
    -0.99
    chaise
    -0.98
    idé
    -0.97
    hamcrest
    -0.97
    ksz
    -0.97
    plak
    -0.97
     είναι
    -0.96
    POSITIVE LOGITS
    e
    1.17
    w
    1.09
    b
    1.09
    t
    1.09
    d
    1.07
    v
    1.05
    m
    1.02
    IT
    1.02
    a
    1.01
    let
    1.00
    Activations Density 0.000%

    No Known Activations