© 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. 34-GEMMASCOPE-RES-131K
    7. 54329
    Prev
    Next
    INDEX
    Explanations

    mercury (Hg), electromyography, Go, porous, prevalence

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

    tokens that appear in scholarly or technical documents, with higher activation for proper names and technical terms.

    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_34/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
    タケ
    -0.78
     uploading
    -0.78
    Revista
    -0.77
    ggt
    -0.77
    上传
    -0.75
    アント
    -0.75
    Torino
    -0.75
     Torino
    -0.75
    ción
    -0.74
    Roz
    -0.72
    POSITIVE LOGITS
     Worcester
    0.81
     lup
    0.79
    peper
    0.78
     AVR
    0.77
    خواندن
    0.75
    irão
    0.71
    ulieren
    0.71
     Umb
    0.70
     گردد
    0.70
     Rwand
    0.69
    Activations Density 0.022%

    No Known Activations