© 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. 48568
    Prev
    Next
    INDEX
    Explanations

    God, Copyright, United

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

    The neuron strongly fires on longer capitalized fragments that are part of proper names or titles (e.g. names of people, companies, document headings).

    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
    смотрим
    -0.87
    かれています
    -0.86
    Lama
    -0.79
    ;">
    -0.77
    囲
    -0.76
    presse
    -0.74
     jejich
    -0.74
    anggap
    -0.73
     invitamos
    -0.71
     flesta
    -0.71
    POSITIVE LOGITS
    TableBody
    0.87
     aiming
    0.75
     united
    0.71
     Soro
    0.70
    dostęp
    0.69
    ừa
    0.69
     Autre
    0.68
     Consultez
    0.67
    Aim
    0.67
     United
    0.67
    Activations Density 0.019%

    No Known Activations