© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15068
    Prev
    Next
    INDEX
    Explanations

    creative processes and writing

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

    This neuron fires on words that describe creative or artistic qualities (e.g. “creative,” “poetic,” “artistic,” “reflective”).

    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
    \
    -2.89
    e
    -1.94
    ’
    -1.92
    ve
    -1.88
    *,
    -1.80
     imple
    -1.73
     fixes
    -1.70
    橚
    -1.70
    '''
    -1.63
    只剩
    -1.63
    POSITIVE LOGITS
    垕
    1.94
    ?”
    1.82
    pagnols
    1.80
     hören
    1.69
    tedrale
    1.62
     jenen
    1.54
    剮
    1.54
     andern
    1.54
     dergleichen
    1.54
    ):
    1.53
    Activations Density 0.009%

    No Known Activations