© 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. 70706
    Prev
    Next
    INDEX
    Explanations

    Jill Dixon, panic:, [What, [Effect, Mouse models

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

    paragraph breaks or newline characters in text.

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

    The neuron fires strongly on the word “technology.”

    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
    chinelo
    -0.97
    kawasaki
    -0.95
     italiani
    -0.95
     selanjutnya
    -0.94
    הם
    -0.94
     Luglio
    -0.94
     Primaria
    -0.94
     utafiti
    -0.93
    tubers
    -0.92
    딧
    -0.92
    POSITIVE LOGITS
    ウ
    0.86
    についても
    0.85
    絝
    0.83
    alini
    0.82
    solver
    0.80
    トレー
    0.79
     asequ
    0.78
     nécess
    0.77
    都好
    0.77
    брать
    0.77
    Activations Density 0.000%

    No Known Activations