© 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. 58950
    Prev
    Next
    INDEX
    Explanations

    chemical substituents

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

    chemical compound numbering notation like "2,3-" or "1,4-" in scientific and chemical 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
    先生が
    -1.54
    となっています
    -1.49
     allmäh
    -1.48
    食べ物
    -1.48
     neuesten
    -1.46
     endgül
    -1.45
     nächsten
    -1.43
    が欲しい
    -1.42
     potrebbe
    -1.42
     wahren
    -1.41
    POSITIVE LOGITS
    NOWLEDG
    1.56
    rø
    1.46
    crocs
    1.45
     of
    1.41
     двух
    1.39
     snd
    1.38
     Meksika
    1.36
     hjem
    1.36
     citoyens
    1.35
    čili
    1.32
    Activations Density 0.179%

    No Known Activations