© 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. 20739
    Prev
    Next
    INDEX
    Explanations

    tetra compounds and syndromes

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

    chemical prefixes like "tetra" and acronyms like "ICS" in scientific or legal texts.

    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
     "
    -3.80
     They
    -3.39
     $^{\
    -3.20
    ↵
    -2.95
    li
    -2.86
    ur
    -2.59
    豋
    -2.56
    ot
    -2.55
    et
    -2.53
    禤
    -2.52
    POSITIVE LOGITS
    美国的
    2.67
    .“
    2.66
    珦
    2.61
    ,
    2.34
     größere
    2.30
    媖
    2.27
    時間も
    2.25
     destacado
    2.25
     “
    2.23
     desaparecido
    2.22
    Activations Density 0.026%

    No Known Activations