© 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. 89982
    Prev
    Next
    INDEX
    Explanations

    low density lipoprotein

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

    technical terms in programming, legal, and scientific documents.

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

    The neuron fires on domain‐specific terminology—especially multi-letter acronyms, proper nouns, and technical identifiers.

    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
    alignSelf
    -0.79
    yal
    -0.71
    Или
    -0.69
    菴
    -0.68
     Или
    -0.68
    выше
    -0.68
     founders
    -0.66
     Farbe
    -0.66
    呈现
    -0.65
    Forums
    -0.65
    POSITIVE LOGITS
    Feel
    0.73
    Packed
    0.71
    カツ
    0.70
    ónima
    0.70
    urazione
    0.69
    Giving
    0.69
     CIS
    0.67
    ƚ
    0.67
     Kola
    0.67
    Picture
    0.67
    Activations Density 0.031%

    No Known Activations