© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67327
    Prev
    Next
    INDEX
    Explanations

    technical, mathematical, biological, and programming terms

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

    HTML/markup elements or code syntax in technical documentation.

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

    The neuron fires on plural nouns (common nouns in their plural form).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     churras
    -1.11
     churrasco
    -1.01
     cavalo
    -0.92
     barbacoa
    -0.92
     azule
    -0.90
    esía
    -0.86
     warung
    -0.86
     plă
    -0.85
     pesso
    -0.84
    bangun
    -0.84
    POSITIVE LOGITS
    pportun
    0.93
    andt
    0.84
     page
    0.82
    가
    0.79
     tomato
    0.79
    anode
    0.77
    tillery
    0.77
     authorization
    0.77
     encantó
    0.77
     encantan
    0.76
    Activations Density 0.131%

    No Known Activations