© 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. 34257
    Prev
    Next
    INDEX
    Explanations

    references and headings

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

    The neuron selectively activates on numeric tokens (standalone numbers, digits, and numeric sequences) 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
    '
    -1.27
     as
    -1.20
     find
    -1.18
     might
    -1.16
    <u>
    -1.15
    N
    -1.13
    [
    -1.13
    it
    -1.07
    I
    -1.06
    &
    -1.06
    POSITIVE LOGITS
    tarta
    1.30
    Tahun
    1.30
    
    1.27
    osoba
    1.23
    Kamera
    1.22
    französ
    1.20
     dérou
    1.18
    Tämä
    1.17
    資料來源
    1.17
    Kurs
    1.16
    Activations Density 0.008%

    No Known Activations