© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49835
    Prev
    Next
    INDEX
    Explanations

    proton and acid ionization

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

    chemical and scientific terminology related to acids, pH, and molecular properties.

    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_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
     snippetHide
    -0.79
    tudiant
    -0.79
    TestMethod
    -0.78
    PageModule
    -0.77
     Buenos
    -0.76
    PostConstruct
    -0.73
     Hyperion
    -0.71
     polymerase
    -0.70
    渇
    -0.69
     reductase
    -0.69
    POSITIVE LOGITS
     proton
    1.52
    proton
    1.47
     dissociation
    1.39
     weak
    1.30
     dissoci
    1.23
     acid
    1.22
     Proton
    1.21
     undis
    1.17
    弱
    1.16
    Proton
    1.13
    Activations Density 0.065%

    No Known Activations