© 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. 54196
    Prev
    Next
    INDEX
    Explanations

    places, religions, medical terms, substances

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

    words related to physical locations, tools, and professions, often with focus on specialized items or places.

    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
    轳
    -1.02
    y
    -0.99
    </b>
    -0.94
    <sub>
    -0.90
    RE
    -0.88
    facing
    -0.88
    Nov
    -0.87
     rejoindre
    -0.87
     somewhat
    -0.86
    wah
    -0.86
    POSITIVE LOGITS
    *}[
    1.05
    organiser
    1.05
     böyle
    1.04
     membuk
    1.03
     julk
    1.02
     рыбы
    1.01
    atleta
    0.99
     facturas
    0.98
    Története
    0.98
     beroperasi
    0.98
    Activations Density 0.093%

    No Known Activations