© 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. 22-GEMMASCOPE-RES-131K
    7. 75152
    Prev
    Next
    INDEX
    Explanations

    regulates PI, potential therapeutic

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

    coordinate structures connected by "and".

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

    The neuron fires on formal academic and scientific terminology—words that signal institutional lectures, research contexts, or specialized laboratory processes.

    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
    蘚
    -0.91
    oltán
    -0.88
     ਨਾਲ
    -0.87
    essy
    -0.85
     البيانات
    -0.85
    etsk
    -0.84
     Benzema
    -0.82
    bores
    -0.81
    CB
    -0.81
     smoker
    -0.81
    POSITIVE LOGITS
     of
    1.16
    upuesto
    0.84
    utveck
    0.80
     生地
    0.76
     genç
    0.75
    ]%
    0.74
    鸽
    0.74
    Ⓣ
    0.72
    maquina
    0.72
    vaccine
    0.71
    Activations Density 0.222%

    No Known Activations