© 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. 35313
    Prev
    Next
    INDEX
    Explanations

    numbers followed by descriptors

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

    The neuron activates on standalone numeric tokens (digits or multi‐digit numbers) wherever they appear 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
    significantly
    -1.50
    begins
    -1.38
     sorgfältig
    -1.38
    completely
    -1.37
    becomes
    -1.36
    become
    -1.36
    produces
    -1.35
    remains
    -1.35
    seems
    -1.34
     této
    -1.34
    POSITIVE LOGITS
     for
    1.51
     will
    1.50
     is
    1.50
     their
    1.48
     after
    1.42
     from
    1.41
     first
    1.39
     There
    1.36
     just
    1.34
     when
    1.32
    Activations Density 0.020%

    No Known Activations