© 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. 22-GEMMASCOPE-RES-131K
    7. 33718
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and compositions

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

    chemical formulas and molecular structures, particularly focusing on carbon (C) and hydrogen (H) atoms.

    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_22/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
    eloma
    -1.35
     dát
    -1.27
    マンガ
    -1.25
     aima
    -1.19
    blood
    -1.19
    1
    -1.16
    éd
    -1.16
     kb
    -1.15
     muchas
    -1.14
     SYSTEM
    -1.14
    POSITIVE LOGITS
     ensures
    1.63
     our
    1.54
    écoute
    1.43
     často
    1.38
     creates
    1.30
     chậm
    1.29
     serves
    1.28
     caters
    1.27
     encourages
    1.26
     prepares
    1.25
    Activations Density 0.041%

    No Known Activations