© 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. 98536
    Prev
    Next
    INDEX
    Explanations

    electrolytes, solvents, and solid-state materials

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

    words and phrases related to battery and electrolyte technology in scientific documents.

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

    The neuron selectively fires on mentions of “electrolyte” (and closely related electrolytic terms) in the text.

    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
     vaccinations
    -0.83
    ieten
    -0.75
     vaccination
    -0.75
    ológica
    -0.74
     arcos
    -0.73
    туаль
    -0.73
    byId
    -0.72
    typescript
    -0.71
     lawyer
    -0.70
     insulin
    -0.70
    POSITIVE LOGITS
     electrolyte
    2.14
     electrolytes
    1.72
     separator
    1.09
     separators
    0.91
     Separator
    0.88
    แข
    0.82
     Apre
    0.82
    separator
    0.81
     salt
    0.76
     cath
    0.76
    Activations Density 0.049%

    No Known Activations