© 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. 47864
    Prev
    Next
    INDEX
    Explanations

    carbon compounds and materials

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

    references to carbon-based materials and compounds.

    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
    嗞
    -3.00
    𞤢
    -2.53
    
    -2.39
    ឣ
    -2.38
    ruguay
    -2.28
     Prancis
    -2.17
     rajut
    -2.14
    鹮
    -2.13
     glimmer
    -2.08
    
    -2.06
    POSITIVE LOGITS
    H
    2.27
    ！】
    2.27
     has
    2.23
    ｘ
    2.13
    <em>
    2.09
    
    2.06
    および
    2.06
    ization
    2.05
    各大
    1.98
    arraycopy
    1.96
    Activations Density 0.024%

    No Known Activations