© 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. 73748
    Prev
    Next
    INDEX
    Explanations

    Galectin, Women, Saturday, Nasr

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

    This neuron activates on new paragraphs, particularly in formal or technical documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on the exact word “working.”

    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
     allemand
    -0.91
     zult
    -0.87
     krijgt
    -0.86
     krig
    -0.83
    cellulose
    -0.82
    ekse
    -0.82
    ローラ
    -0.82
    brainly
    -0.82
     découv
    -0.82
     suivi
    -0.81
    POSITIVE LOGITS
     manchmal
    0.94
     protože
    0.83
    Поэтому
    0.82
     circumference
    0.79
     dergleichen
    0.77
     discussed
    0.77
     tetto
    0.74
     because
    0.73
     ❤
    0.72
     wundersch
    0.72
    Activations Density 0.000%

    No Known Activations