© 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. 11829
    Prev
    Next
    INDEX
    Explanations

    Keystone XL, Sherwood Rowland

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

    names and scientific terms, particularly "Keystone" and variations of "Sherwood" as proper nouns.

    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
    }
    -4.00
    ".
    -2.77
    al
    -2.72
    the
    -2.64
    2
    -2.61
    </h3>
    -2.53
    ")
    -2.50
    t
    -2.44
    .
    -2.39
    """
    -2.25
    POSITIVE LOGITS
    
    2.70
    鮠
    2.69
    鑠
    2.48
    ጁ
    2.44
    жений
    2.39
    🛖
    2.39
     burbu
    2.28
     préféré
    2.27
    䉴
    2.23
    几个
    2.22
    Activations Density 0.002%

    No Known Activations