© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65904
    Prev
    Next
    INDEX
    Explanations

    acid and related acids

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

    chemical terms related to acids (like "carboxylic acid," "phosphoric acid," "triflic acid," etc.) in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on chemical acid names and related terminology (e.g. “phosphoric,” “benzoic,” “malonic,” “formic,” “lactic,” “carboxylic,” “acid,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    地下鉄
    -0.77
     dieťa
    -0.76
     sulfate
    -0.75
     carbonates
    -0.73
     granule
    -0.72
     الشيخ
    -0.72
     všetky
    -0.69
     KCl
    -0.69
     ofreció
    -0.69
    uestran
    -0.68
    POSITIVE LOGITS
     acid
    2.08
     acids
    1.66
    COOH
    1.47
     ácido
    1.45
     Acid
    1.44
    acid
    1.35
     Acids
    1.35
    Acid
    1.30
     acetic
    1.29
    acids
    1.23
    Activations Density 0.126%

    No Known Activations