© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54293
    Prev
    Next
    INDEX
    Explanations

    Joseph Powell, slightly better financial

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

    The neuron strongly activates on financial‐news prose—especially business‐and‐market terminology describing competition, corporate pressures, customers, and contracts.

    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
     chré
    -1.95
     religieuses
    -1.66
     religieux
    -1.46
     گیاه
    -1.36
     katholischen
    -1.32
     sogenannten
    -1.31
     kvinna
    -1.30
     kuliner
    -1.26
     جع
    -1.24
     eccl
    -1.20
    POSITIVE LOGITS
    ּוֹ
    1.74
    וּ
    1.63
    ֶּ
    1.48
     we
    1.44
    ִּ
    1.32
     брюки
    1.30
    Ahoj
    1.24
     سبورت
    1.23
    фильм
    1.23
    циал
    1.23
    Activations Density 0.025%

    No Known Activations