© 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. 10-GEMMASCOPE-RES-131K
    7. 110578
    Prev
    Next
    INDEX
    Explanations

    creating effects or consequences

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

    The neuron detects occurrences of the root “creat” in its various inflected forms (create, creates, created, creating).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -2.05
    鹇
    -2.00
    甍
    -1.81
    姈
    -1.73
    despite
    -1.73
    殽
    -1.70
    𓆏
    -1.70
     pérd
    -1.67
     ſta
    -1.64
    齶
    -1.64
    POSITIVE LOGITS
     ktoré
    1.79
     které
    1.74
    řízen
    1.66
    </h4>
    1.65
     môže
    1.57
     contado
    1.56
    垕
    1.54
     myös
    1.52
     The
    1.50
     også
    1.50
    Activations Density 0.034%

    No Known Activations