© 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. 55669
    Prev
    Next
    INDEX
    Explanations

    medical, technical, and legal terms

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

    programming code, markup languages, and technical documentation formatting elements.

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

    The neuron fires most strongly on rare or domain-specific “content” tokens—uncommon technical or jargon words (including specialized nouns and terms) rather than common function 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
     Wunsch
    -0.76
     enseñ
    -0.69
     goes
    -0.68
    請求
    -0.67
    medskip
    -0.66
     לך
    -0.66
     动物
    -0.63
    축
    -0.63
    unchecked
    -0.61
     ultrasonic
    -0.61
    POSITIVE LOGITS
     badges
    0.67
     hong
    0.67
    拷贝
    0.66
    жны
    0.66
     IFTTT
    0.65
    ($('#
    0.65
     REV
    0.64
     HJ
    0.63
     PHIL
    0.63
     СО
    0.62
    Activations Density 0.076%

    No Known Activations