© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25103
    Prev
    Next
    INDEX
    Explanations

    RNA polymerase

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

    variables, parameters, and content references in programming code.

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

    The neuron fires on single tokens that contain both uppercase and lowercase letters—i.e. mixed-case identifiers or camel-style names.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     deciso
    -1.00
    いかがでしたか
    -0.93
     visitare
    -0.92
    وها
    -0.91
     this
    -0.91
    Răsp
    -0.90
    Kult
    -0.90
     AÑO
    -0.90
     Añade
    -0.89
     cittad
    -0.88
    POSITIVE LOGITS
    ficiencia
    1.01
    ablen
    0.92
     gänzlich
    0.90
    <b>
    0.88
     beziehungs
    0.86
    んでる
    0.83
    ඔ
    0.83
     gearbeitet
    0.83
    AGES
    0.82
     ¢
    0.82
    Activations Density 0.043%

    No Known Activations