© 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. 22-GEMMASCOPE-RES-131K
    4. 424
    Prev
    Next
    INDEX
    Explanations

    biological classification and scientific terms

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

    abbreviated terms or technical identifiers in scientific or technical documents.

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

    The neuron fires strongly on technical or scientific content words—domain‐specific nouns like “family,” “ParA,” “bone,” “spring,” “novel,” “glyco,” or “atomizing”—that typically appear in paper titles, headings, or terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    nasel
    -1.06
    imbangan
    -0.88
     kartu
    -0.87
     turist
    -0.86
     responsab
    -0.84
    باب
    -0.84
    alisis
    -0.83
    Atelier
    -0.83
     parlamento
    -0.81
     voluto
    -0.81
    POSITIVE LOGITS
     Duitse
    0.84
     vorhandenen
    0.83
     Проци
    0.83
     freio
    0.82
     首页
    0.82
    like
    0.81
     onderstaande
    0.81
     conexão
    0.81
    oni
    0.79
    rii
    0.79
    Activations Density 0.111%

    No Known Activations