© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68291
    Prev
    Next
    INDEX
    Explanations

    questions or lists

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

    The neuron is triggered by numeric tokens—especially multi‐digit numbers.

    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
    رحلة
    -1.30
     four
    -1.26
     several
    -1.24
     five
    -1.21
     revisor
    -1.20
     prata
    -1.18
     eight
    -1.15
     Three
    -1.15
     During
    -1.14
     revised
    -1.14
    POSITIVE LOGITS
     enlever
    1.09
    を書
    1.09
    氿
    1.08
     trám
    1.05
     
    1.05
     REALLY
    1.05
     bijna
    1.03
     Dinas
    1.02
     dát
    1.02
     gigantic
    1.02
    Activations Density 0.000%

    No Known Activations