© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103869
    Prev
    Next
    INDEX
    Explanations

    creative vision and artistry

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

    The neuron fires on words that evoke creative or artistic concepts—terms like “vision,” “artistic(ally),” “creativity,” “artistry,” and similar expressions of creative expression.

    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
     to
    -1.37
     яка
    -1.25
    ’
    -1.23
     появится
    -1.21
    );
    -1.20
     Facing
    -1.18
     Variante
    -1.13
     научно
    -1.09
     tollen
    -1.09
    Seems
    -1.09
    POSITIVE LOGITS
     very
    1.45
     quite
    1.37
     certainly
    1.30
     probably
    1.30
     sometimes
    1.27
     собственности
    1.26
     wenigen
    1.25
     loosely
    1.24
     people
    1.23
     possibly
    1.23
    Activations Density 0.055%

    No Known Activations