© 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. 71354
    Prev
    Next
    INDEX
    Explanations

    amyotrophic lateral sclerosis

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

    technical terminology related to scientific or engineering systems, particularly in medical, electrical, and mechanical domains.

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

    The neuron selectively activates on specialized technical jargon and terminology typical of scientific or engineering texts.

    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
    getPackageName
    -1.20
    ığım
    -1.18
    🍨
    -1.12
     可爱
    -1.11
    dhism
    -1.10
    ásticos
    -1.09
     you
    -1.08
    США
    -1.07
    kozó
    -1.07
    %
    
    -1.06
    POSITIVE LOGITS
     not
    1.26
     Uniwersyte
    1.11
     up
    1.05
     about
    1.05
    在哪
    1.04
     cualquier
    1.02
     pierdas
    1.02
    ,
    1.01
    али
    1.01
     of
    0.99
    Activations Density 0.132%

    No Known Activations