© 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. 10-GEMMASCOPE-RES-131K
    7. 102804
    Prev
    Next
    INDEX
    Explanations

    Far, Farc, Farn, Farah, Faris, Pharrell

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

    The neuron specifically detects occurrences of “farnesyl” (and its variants like farnesylation/farnesylated) in biochemical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     atendido
    -2.75
    ﻒ
    -2.52
     decidido
    -2.50
     porcent
    -2.42
     bocas
    -2.42
    蟜
    -2.39
     vivido
    -2.39
     cortinas
    -2.38
     revelado
    -2.36
     ͡°
    -2.34
    POSITIVE LOGITS
    e
    3.56
     They
    3.17
    x
    3.11
     When
    2.41
     "
    2.38
    b
    2.34
    Y
    2.34
     lorsqu
    2.34
    .
    2.33
    er
    2.30
    Activations Density 0.007%

    No Known Activations