© 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. 10509
    Prev
    Next
    INDEX
    Explanations

    lime and Lyme

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

    words related to "lime" or "limelight", including references to the chemical (calcium hydroxide) and the color.

    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
     vollständige
    -3.08
     sichere
    -2.78
     “(
    -2.63
     wichtigste
    -2.56
     eigentliche
    -2.56
     dopo
    -2.48
     verbess
    -2.48
     verfügb
    -2.45
    大約
    -2.45
     “.
    -2.45
    POSITIVE LOGITS
    </strong>
    3.67
    e
    2.31
            
    2.23
    大学の
    2.20
     connus
    2.14
    喈
    2.09
     normaux
    2.08
     ผ้า
    2.05
     ฝ
    2.02
     apparaissent
    2.02
    Activations Density 0.004%

    No Known Activations