© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84519
    Prev
    Next
    INDEX
    Explanations

    halogen and its compounds

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

    references to halogen or halogenated compounds.

    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
     обеспечить
    -2.84
    vantaged
    -2.75
    宬
    -2.69
    噥
    -2.64
    噲
    -2.59
    ✨:
    -2.47
    哢
    -2.47
    曁
    -2.45
     แต่
    -2.41
    шего
    -2.38
    POSITIVE LOGITS
    {
    3.80
     \
    3.02
    2
    2.70
     
    2.61
    ,,
    2.52
     gdyż
    2.47
    1
    2.47
     '
    2.47
    }
    2.36
    ]
    2.34
    Activations Density 0.005%

    No Known Activations