© 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. 129654
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially decimal‐formatted statistics—and related punctuation in sports‐stat contexts.

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

    numbers and counts

    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
     cuja
    -1.14
     instruk
    -1.02
    Terima
    -1.00
     poži
    -1.00
    durante
    -0.99
    ﻻ
    -0.95
    tipps
    -0.95
    mitglieder
    -0.95
     musíte
    -0.94
     新品
    -0.93
    POSITIVE LOGITS
     by
    1.17
     two
    1.02
     three
    0.99
    はお
    0.92
     with
    0.91
     penalty
    0.90
     question
    0.89
    萝卜
    0.89
     four
    0.88
    ContextCompat
    0.88
    Activations Density 0.002%

    No Known Activations