© 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. 10-GEMMASCOPE-RES-131K
    7. 105181
    Prev
    Next
    INDEX
    Explanations

    National Libraries and Health Institutes

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

    references to libraries, archives, and cultural institutions like the Library of Congress or National Library.

    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_10/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
     This
    -1.92
    The
    -1.74
    LARATION
    -1.52
     juſ
    -1.48
     perdidos
    -1.48
    🧌
    -1.45
    this
    -1.41
    
    -1.40
     Télé
    -1.40
     ,‬
    -1.38
    POSITIVE LOGITS
     ajud
    1.65
     &
    1.53
     erst
    1.43
    </h2>
    1.39
     than
    1.34
    isation
    1.34
    那时
    1.31
    كتشاف
    1.30
     yra
    1.28
     vetor
    1.28
    Activations Density 0.005%

    No Known Activations