© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68422
    Prev
    Next
    INDEX
    Explanations

    cola, coke, and cocaine

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

    Coca-Cola and other cola brand references in text.

    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
     hilarious
    -2.55
    ri
    -2.50
    聍
    -2.44
     immeasurable
    -2.41
    be
    -2.41
    五六
    -2.41
     教程
    -2.36
     gleiche
    -2.34
     информацию
    -2.31
    甚至
    -2.30
    POSITIVE LOGITS
    釭
    2.56
    嵜
    2.08
    2.03
    洋服
    2.02
    zelfde
    2.00
    風邪
    2.00
     originalen
    1.99
     видеть
    1.99
     ])
    1.93
     verhind
    1.92
    Activations Density 0.004%

    No Known Activations