© 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. 127854
    Prev
    Next
    INDEX
    Explanations

    chemical nomenclature and compounds

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

    chemical formulas and organic compound names, particularly those with nitrogen and oxygen-containing functional groups.

    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
    Edmonton
    -1.50
     denominado
    -1.44
     but
    -1.36
    лении
    -1.35
     októ
    -1.32
     república
    -1.28
     nedost
    -1.27
     ayuntamiento
    -1.26
     čia
    -1.25
    ciutto
    -1.25
    POSITIVE LOGITS
     bleiben
    1.19
    d
    1.13
    }
    1.12
     Teufel
    1.11
     dwie
    1.11
     dijeron
    1.10
     Beine
    1.10
    wsze
    1.09
    ve
    1.07
    なと
    1.07
    Activations Density 0.074%

    No Known Activations