© 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. 10-GEMMASCOPE-RES-131K
    7. 86837
    Prev
    Next
    INDEX
    Explanations

    post-apocalyptic, complement, ambulatory, enamel

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

    The neuron responds to multi‐syllabic, domain-specific technical terms (especially those with Greek or Latin roots).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ECM
    -1.61
     возможности
    -1.48
    hermosa
    -1.46
     precisamente
    -1.41
    ️
    -1.38
    xiii
    -1.35
    rendre
    -1.34
     consequent
    -1.34
    mathrm
    -1.33
     respuestas
    -1.32
    POSITIVE LOGITS
     would
    1.66
    f
    1.43
     seems
    1.32
     only
    1.30
     Adding
    1.30
     unrelenting
    1.29
     paesi
    1.29
     incessant
    1.27
     Seems
    1.26
     may
    1.23
    Activations Density 0.126%

    No Known Activations