© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20854
    Prev
    Next
    INDEX
    Explanations

    chemical moieties or form factors

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

    chemical and technical terms, particularly suffixes like 'ieties', 'factor', 'way', and 'pathology'.

    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
    </h5>
    -1.81
    %;
    -1.73
     Einfluß
    -1.66
    </h3>
    -1.63
    
    -1.62
     или
    -1.51
     Eindruck
    -1.51
     attorno
    -1.51
     einzigen
    -1.50
     improves
    -1.49
    POSITIVE LOGITS
    陡
    1.56
    Ҭ
    1.56
     –
    1.52
    ,
    1.49
     &
    1.48
     clich
    1.44
    了你
    1.41
     dahil
    1.40
     esche
    1.40
    K
    1.39
    Activations Density 0.276%

    No Known Activations