© 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. 34-GEMMASCOPE-RES-131K
    4. 84288
    Prev
    Next
    INDEX
    Explanations

    scientific contexts with specific terms

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

    scientific notation and terminology in academic papers.

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

    The neuron fires on small tokens that include internal punctuation (dashes or dots)—for example, hyphenated prefixes (“sec-”), abbreviated forms (“sub.”, “i.e.”), and similar short punctuated pieces.

    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
     polisi
    -0.90
     by
    -0.85
    логических
    -0.84
    dfn
    -0.84
    ogues
    -0.84
    rentino
    -0.84
     umumnya
    -0.83
    iyor
    -0.83
     bendera
    -0.83
    🌤
    -0.82
    POSITIVE LOGITS
    Fig
    1.13
     chapter
    0.99
     Fig
    0.96
     doi
    0.92
    Chapter
    0.92
    試試
    0.91
    doi
    0.89
     swoje
    0.88
    liu
    0.86
     Chapter
    0.85
    Activations Density 0.020%

    No Known Activations