© 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. 70515
    Prev
    Next
    INDEX
    Explanations

    stimulation of nerves

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

    physical manipulation or stimulation of body parts or tissues in scientific and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     وقع
    -1.06
    在那里
    -1.02
     قام
    -1.00
     všech
    -0.99
    ในการ
    -0.91
    eping
    -0.89
     gimnas
    -0.88
     díky
    -0.88
     качестве
    -0.87
    dicionado
    -0.87
    POSITIVE LOGITS
     at
    1.31
    ίναι
    1.03
     zape
    0.98
     through
    0.93
     verdaderas
    0.91
     maravillosas
    0.90
    Tento
    0.88
    Více
    0.85
     directly
    0.84
     invitaciones
    0.84
    Activations Density 0.151%

    No Known Activations