© 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. 67202
    Prev
    Next
    INDEX
    Explanations

    resin, coatings, pigments, surfactants, catalysts

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

    chemical compounds and technical terminology in scientific or industrial contexts.

    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
    iress
    -1.48
    ֠
    -1.44
    お子
    -1.36
     hongos
    -1.32
    øver
    -1.30
    pantaloni
    -1.30
    columnwidth
    -1.28
     baloncesto
    -1.27
     hắn
    -1.27
    ského
    -1.27
    POSITIVE LOGITS
     in
    1.65
     product
    1.52
     products
    1.39
     debe
    1.34
    מבר
    1.30
     творо
    1.22
     suatu
    1.19
    tanleria
    1.19
     industry
    1.18
     skrev
    1.18
    Activations Density 0.171%

    No Known Activations