© 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. 80009
    Prev
    Next
    INDEX
    Explanations

    cross-linked cellulose and gums

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

    chemical ingredients and compounds in product formulations.

    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
     new
    -1.55
     even
    -1.25
     ilustracji
    -1.24
     on
    -1.15
    razos
    -1.14
     kval
    -1.12
     веке
    -1.12
    手上
    -1.10
    zeum
    -1.09
     specifik
    -1.09
    POSITIVE LOGITS
     optimieren
    1.27
    Descriere
    1.15
    眉头
    1.15
    ⾼
    1.13
     zugel
    1.09
     BioLib
    1.09
    怅
    1.09
     gewährleisten
    1.09
     necesarios
    1.08
     gewährle
    1.07
    Activations Density 0.005%

    No Known Activations