© 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. 78988
    Prev
    Next
    INDEX
    Explanations

    prod

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

    This neuron detects occurrences of the “prod-” prefix (as in prodigal, prodromal, or the prod field).

    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
     candidats
    -0.79
    訛
    -0.75
    embry
    -0.72
    rne
    -0.72
    getState
    -0.72
    ishu
    -0.71
     acreditar
    -0.70
     abrazo
    -0.69
    éfono
    -0.69
     Karriere
    -0.69
    POSITIVE LOGITS
     прод
    0.83
     prod
    0.81
     Prodi
    0.79
     transcribed
    0.72
    зин
    0.71
    Кру
    0.69
     Prod
    0.68
    Lietu
    0.67
     productivity
    0.67
     tess
    0.66
    Activations Density 0.028%

    No Known Activations