© 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. 55998
    Prev
    Next
    INDEX
    Explanations

    code punctuation followed by keywords

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

    The neuron fires on numeric literals (integer constants) in code snippets.

    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
     in
    -3.89
     with
    -3.39
     as
    -3.36
     at
    -3.25
     to
    -3.11
     on
    -2.97
     for
    -2.97
     without
    -2.81
     from
    -2.81
     but
    -2.69
    POSITIVE LOGITS
     diriger
    3.16
     maniere
    2.98
     délais
    2.80
     remé
    2.75
     rése
    2.75
    
    2.70
     plafon
    2.69
     accompagner
    2.67
     refroid
    2.64
     bascul
    2.64
    Activations Density 0.156%

    No Known Activations