© 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. 59693
    Prev
    Next
    INDEX
    Explanations

    base excess, pH, buffers

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

    technical or scientific content related to chemical solutions, pH levels, and acid-base relationships.

    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
    England
    -0.79
    offsetHeight
    -0.78
     Existenz
    -0.77
    bounds
    -0.75
     reloadData
    -0.72
    ]>=
    -0.72
     productivity
    -0.71
    ỳnh
    -0.70
     czyn
    -0.69
    öszi
    -0.69
    POSITIVE LOGITS
    ἡ
    0.76
    unused
    0.75
     Lait
    0.75
     hydrolysis
    0.73
     Buff
    0.73
    wijl
    0.71
    Schemes
    0.71
    ADDED
    0.71
     श्री
    0.71
     dissociation
    0.71
    Activations Density 0.005%

    No Known Activations