© 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. 64402
    Prev
    Next
    INDEX
    Explanations

    film producer

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

    The neuron activates on mentions of “producer” or “production” roles and related job titles.

    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
     conocidas
    -1.36
    “
    -1.25
    についての
    -1.25
     recientemente
    -1.17
    扮演
    -1.16
     verkau
    -1.16
     upgraded
    -1.13
    反应过来
    -1.12
    研究
    -1.10
    n
    -1.10
    POSITIVE LOGITS
     and
    1.49
    และ
    1.41
     of
    1.24
     bersih
    1.23
    ấu
    1.20
    rire
    1.17
     موب
    1.17
     sekaligus
    1.17
    dáms
    1.16
     continente
    1.16
    Activations Density 0.031%

    No Known Activations