© 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. 128755
    Prev
    Next
    INDEX
    Explanations

    The neuron responds whenever it sees a standalone numeric token (i.e. sequences of digits).

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

    headings and technical terms

    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
    ınızı
    -1.25
     måneder
    -1.16
     borbo
    -1.13
     mikina
    -1.13
    henti
    -1.13
    corrhi
    -1.11
     manquante
    -1.11
    nimi
    -1.10
    ocardial
    -1.09
    салат
    -1.09
    POSITIVE LOGITS
    r
    1.37
    T
    1.34
    l
    1.34
    k
    1.30
    B
    1.26
    n
    1.26
    j
    1.26
    to
    1.25
    p
    1.21
    w
    1.20
    Activations Density 0.000%

    No Known Activations