© 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. 13002
    Prev
    Next
    INDEX
    Explanations

    numbers and letters followed by specific words

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

    The neuron detects uppercase biomedical acronyms (e.g. “VSMCs”).

    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
    providedIn
    -1.27
     because
    -1.24
     fej
    -1.11
     sombras
    -1.08
     kré
    -1.07
     for
    -1.06
    刹那
    -1.05
    nextProps
    -1.03
    homonymie
    -1.02
    signable
    -1.02
    POSITIVE LOGITS
    就是一个
    1.06
     acoper
    1.05
    四个
    1.05
     erwor
    1.02
    该如何
    1.00
     trecut
    0.96
    : 
    0.96
    などが
    0.93
    还有一个
    0.93
     conglomer
    0.93
    Activations Density 0.000%

    No Known Activations