© 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. 43961
    Prev
    Next
    INDEX
    Explanations

    hydroxy compounds

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

    chemical compounds containing "hydroxy" in their molecular structure.

    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
     to
    -2.30
     včetně
    -1.89
     into
    -1.80
     by
    -1.77
    暮らし
    -1.71
     aparecen
    -1.58
     are
    -1.54
     as
    -1.54
    C
    -1.52
    D
    -1.52
    POSITIVE LOGITS
    3
    2.09
    Nothing
    1.82
    From
    1.82
     the
    1.79
     juillet
    1.79
    我们的
    1.73
    5
    1.73
    鯷
    1.73
     pesa
    1.72
    Only
    1.71
    Activations Density 0.136%

    No Known Activations