© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99368
    Prev
    Next
    INDEX
    Explanations

    medical and health conditions

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

    scientific or medical terms in academic or technical contexts.

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

    The neuron consistently fires on content‐heavy, domain‐specific terms (especially acronyms, proper nouns, and technical jargon).

    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
     extent
    -0.98
     existence
    -0.88
     importance
    -0.88
     Antes
    -0.86
     and
    -0.86
     presence
    -0.86
     copies
    -0.85
     Types
    -0.85
     meaning
    -0.84
     chance
    -0.82
    POSITIVE LOGITS
     TÉCN
    1.13
    dataset
    1.00
     TÉ
    0.90
    shi
    0.89
     Rusi
    0.88
    otoxin
    0.86
     penyakit
    0.86
    deferred
    0.85
    绀
    0.85
    缉
    0.83
    Activations Density 0.192%

    No Known Activations