© 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. 129556
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on standalone numeric tokens (e.g. “240”).

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

    article/question answers

    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
     for
    -1.13
     encompasses
    -1.07
    It
    -1.07
    C
    -1.06
     X
    -1.06
     Only
    -1.06
     to
    -1.05
     has
    -1.03
    For
    -1.02
     C
    -1.01
    POSITIVE LOGITS
    閖
    1.19
     vermel
    1.11
    FOTO
    1.10
    denken
    1.10
     willen
    1.09
     バス
    1.05
     corriger
    1.03
     bailarina
    1.02
    LÄ
    1.01
     важ
    1.00
    Activations Density 0.005%

    No Known Activations