© 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. 67725
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

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

    lists or sequences of items separated by commas or ampersands.

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

    The neuron fires on the main content-bearing nouns or concepts in a sentence (the key topic 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_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
    Produkte
    -1.05
    Erfahrung
    -0.99
    Angebot
    -0.90
    xelles
    -0.90
    Lieferumfang
    -0.84
    Sicherheit
    -0.83
    Bewertung
    -0.83
     Meningkatkan
    -0.82
    Qualität
    -0.81
     餐厅
    -0.80
    POSITIVE LOGITS
    つなが
    0.82
    ourdes
    0.80
    illoma
    0.79
     işte
    0.79
    Speaking
    0.79
    circledR
    0.77
    頃の
    0.77
     musiciens
    0.77
     betweenstory
    0.77
     White
    0.77
    Activations Density 0.134%

    No Known Activations