© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75495
    Prev
    Next
    INDEX
    Explanations

    python imports and file paths

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

    The neuron fires on occurrences of the literal word “distributed” (e.g. package or directory names containing “distributed”).

    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
     truly
    -1.02
     often
    -0.96
     Often
    -0.94
     all
    -0.89
     extraordinary
    -0.87
     like
    -0.87
     pushing
    -0.86
     terribly
    -0.86
     or
    -0.84
     their
    -0.84
    POSITIVE LOGITS
     generali
    1.06
    ilever
    1.04
     sre
    1.04
    helps
    1.01
     (*)
    1.00
     (__
    1.00
    posi
    0.99
     ($.
    0.98
     \_
    0.98
    ⁹
    0.98
    Activations Density 0.013%

    No Known Activations