© 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. 10-GEMMASCOPE-RES-131K
    7. 111946
    Prev
    Next
    INDEX
    Explanations

    key-value pair keys

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

    opening quotation marks in JSON key-value pairs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on quoted numeric literals (especially decimal numbers) in JSON-like 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_10/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
     SUPERIOR
    -1.80
     FEBR
    -1.78
     of
    -1.70
     alip
    -1.69
     MADRID
    -1.66
     FÜR
    -1.60
     TAMB
    -1.59
     اگه
    -1.58
     CANAL
    -1.58
    Якщо
    -1.56
    POSITIVE LOGITS
     in
    2.06
     
    1.91
     estas
    1.76
     is
    1.74
    它的
    1.69
     was
    1.67
    ↵↵
    1.61
     "
    1.55
    Its
    1.54
    ↵
    1.53
    Activations Density 0.010%

    No Known Activations