© 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. 14355
    Prev
    Next
    INDEX
    Explanations

    story of Jacobwe havevisuals likecompanies likeemergence ofresponse fromprintout ofPDE that

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

    The neuron detects numeric tokens (numbers and numerical data) within 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
     самому
    -1.06
     themselves
    -1.03
    就没有
    -1.02
    Ziel
    -1.02
     encontrarás
    -0.99
    ThemeProvider
    -0.94
    自ら
    -0.93
     założ
    -0.91
     itself
    -0.91
    Gilla
    -0.91
    POSITIVE LOGITS
     that
    1.25
     a
    1.17
     here
    1.13
     from
    1.01
    nast
    1.00
     mengucap
    0.98
     sanoo
    0.96
    볶
    0.94
     вместо
    0.94
    юза
    0.93
    Activations Density 0.132%

    No Known Activations