© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36354
    Prev
    Next
    INDEX
    Explanations

    association and competition

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

    The neuron detects tokens that are part of formal organization or corporate names (e.g. multiword institution titles and company abbreviations).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Eben
    -0.90
     用品
    -0.82
     adequate
    -0.82
     ONLY
    -0.81
     бед
    -0.79
    וּ
    -0.79
     some
    -0.79
     LEGO
    -0.78
     teks
    -0.78
    ciona
    -0.77
    POSITIVE LOGITS
    менту
    1.00
     remarkably
    0.87
     largely
    0.85
     luscious
    0.85
    (*
    0.85
     Erinnerungen
    0.83
    时间
    0.83
     Έ
    0.81
     ludicrous
    0.80
     vzor
    0.79
    Activations Density 0.013%

    No Known Activations