© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93173
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

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

    scientific and medical terminology related to biology, particularly plant, cellular, and anatomical terms.

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

    The neuron detects specialized, multi-syllable scientific and biomedical terms and 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
     straips
    -1.18
     Also
    -1.09
    arkhand
    -1.09
    lllllllll
    -1.06
    _
    -1.05
    rrrrr
    -1.04
    I
    -1.04
     Haziran
    -1.03
    ificaciones
    -1.02
    ernes
    -1.02
    POSITIVE LOGITS
     можем
    1.30
    haviours
    1.12
    extremely
    1.08
     promove
    1.07
     asume
    1.04
    ebly
    1.02
    <bos>
    1.02
     talleres
    1.00
     GetEnumerator
    1.00
    ulite
    0.98
    Activations Density 0.935%

    No Known Activations