© 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. 97769
    Prev
    Next
    INDEX
    Explanations

    redistribute copyright license

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

    This neuron spikes on module‐import lines in code (e.g. “import …” or “from … import …”).

    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
    ât
    -0.79
    elimin
    -0.75
    Scenario
    -0.67
    ULLY
    -0.66
     zastos
    -0.66
    zeuge
    -0.66
    inline
    -0.64
    eins
    -0.64
    ❂
    -0.63
    cots
    -0.63
    POSITIVE LOGITS
     phys
    0.73
    englanniksi
    0.72
     Cym
    0.71
    hasil
    0.68
     accorded
    0.68
     MISC
    0.68
     redraw
    0.66
    myArray
    0.66
     Llan
    0.65
     MRC
    0.65
    Activations Density 0.065%

    No Known Activations