© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49528
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    The neuron fires on long, multi-syllable scientific or technical terms (especially Greek/Latin-derived words).

    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
     this
    -2.11
     and
    -1.98
     bringing
    -1.72
     their
    -1.72
     facilitate
    -1.70
     extraordinary
    -1.65
     providing
    -1.64
     supremely
    -1.62
     achieve
    -1.59
     several
    -1.58
    POSITIVE LOGITS
     DURING
    1.73
     AMAZING
    1.61
     rése
    1.59
     horrid
    1.58
     ornate
    1.57
     unending
    1.57
    mbgg
    1.55
     masterful
    1.52
     perpé
    1.50
     progrès
    1.49
    Activations Density 0.931%

    No Known Activations