© 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. 66901
    Prev
    Next
    INDEX
    Explanations

    start of lines or declarations

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

    The neuron selectively activates on numeric tokens—especially floating-point numbers (e.g. “108.5”, “83.5”, “116.5”)—i.e. it detects decimal-format numbers 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
     has
    -1.42
     over
    -1.21
     three
    -1.19
     in
    -1.18
     then
    -1.17
     showed
    -1.17
     so
    -1.15
     gave
    -1.14
     first
    -1.13
     using
    -1.13
    POSITIVE LOGITS
    peteer
    1.14
     brimming
    1.12
     faciliter
    1.12
     ..........
    1.11
     .........
    1.10
     multitudes
    1.07
     luminos
    1.05
     maniere
    1.05
     .......
    1.05
     campagnes
    1.05
    Activations Density 0.000%

    No Known Activations