© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 84422
    Prev
    Next
    INDEX
    Explanations

    sharing or giving freely

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

    The neuron detects instances of the word “share” (in all its forms) indicating acts of sharing.

    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
    '
    -1.78
     my
    -1.39
    さんも
    -1.38
     model
    -1.36
     to
    -1.32
     control
    -1.31
    :
    -1.30
     result
    -1.26
     atriz
    -1.26
     number
    -1.25
    POSITIVE LOGITS
    When
    1.52
     tanken
    1.44
    While
    1.41
    Although
    1.40
    merkungen
    1.40
    they
    1.38
    They
    1.37
    この日は
    1.36
     різних
    1.35
    гії
    1.34
    Activations Density 0.014%

    No Known Activations