© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78290
    Prev
    Next
    INDEX
    Explanations

    finding version numbers

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

    The neuron fires on JSON/YAML structural formatting tokens—especially indentation whitespace and quoting characters that mark keys and values.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     name
    -2.39
     Name
    -1.94
     NAME
    -1.80
    名称
    -1.71
    NAME
    -1.66
    Name
    -1.63
     named
    -1.63
    name
    -1.62
    ByName
    -1.46
    名前
    -1.45
    POSITIVE LOGITS
     lebt
    0.76
     sollte
    0.76
    srcs
    0.71
     pár
    0.70
     age
    0.70
     Однако
    0.69
     возрасте
    0.69
     voglia
    0.69
    序
    0.68
     logo
    0.68
    Activations Density 0.119%

    No Known Activations