© 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. 34-GEMMASCOPE-RES-131K
    7. 65374
    Prev
    Next
    INDEX
    Explanations

    code serialization and data values

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

    The neuron fires on leading whitespace (indentation) tokens in code blocks.

    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
    łbym
    -0.87
     fejles
    -0.78
     teile
    -0.76
    ciaio
    -0.74
     државе
    -0.74
    jupe
    -0.73
     niños
    -0.73
    INTERIOR
    -0.71
    良かった
    -0.71
     fiyat
    -0.71
    POSITIVE LOGITS
    toObject
    1.15
    toJSON
    1.12
    valueOf
    0.83
    東北
    0.81
    ꧂
    0.79
    PyObject
    0.77
    IVATE
    0.77
    மே
    0.77
    ToJson
    0.75
     sows
    0.75
    Activations Density 0.007%

    No Known Activations