© 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. 44234
    Prev
    Next
    INDEX
    Explanations

    creative works or writings

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

    The neuron fires on occurrences of the word “works” (as in creative or scholarly works).

    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
    媗
    -2.94
    炱
    -2.59
    筏
    -2.52
    ୌ
    -2.41
    鱨
    -2.33
    ᭝
    -2.30
    鹛
    -2.27
    isierung
    -2.27
    </h1>
    -2.25
     mily
    -2.22
    POSITIVE LOGITS
    </em>
    3.16
    If
    2.88
    1
    2.73
    It
    2.72
    7
    2.69
    4
    2.61
    9
    2.59
    In
    2.59
    5
    2.56
    3
    2.55
    Activations Density 0.007%

    No Known Activations