© 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. 34-GEMMASCOPE-RES-131K
    7. 64534
    Prev
    Next
    INDEX
    Explanations

    unit testing or code

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

    The neuron strongly activates on unusually long tokens (sequences of many characters), regardless of whether they’re letters, digits, or symbols.

    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
     thirty
    -0.78
    siert
    -0.75
    żesz
    -0.73
     هفته
    -0.71
    Buy
    -0.69
    btnAdd
    -0.68
    pw
    -0.68
    Nullable
    -0.67
    kopf
    -0.66
    deleteById
    -0.66
    POSITIVE LOGITS
    orna
    0.84
     Matsumoto
    0.73
     Reeve
    0.72
    дний
    0.70
     imageNamed
    0.70
    REW
    0.70
    ṽ
    0.69
    reducer
    0.69
    TestRunner
    0.69
    cola
    0.68
    Activations Density 0.219%

    No Known Activations