© 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. 71748
    Prev
    Next
    INDEX
    Explanations

    spend your time on

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

    This neuron fires on terms referring to scarce resources (especially money, time, space, etc.) and words about spending, allocating, or competing for those resources.

    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
     zoals
    -1.33
    遢
    -1.30
    ossed
    -1.27
     Contributing
    -1.23
     مانند
    -1.21
     السيارات
    -1.19
     już
    -1.18
    年来
    -1.16
     肩
    -1.15
     its
    -1.13
    POSITIVE LOGITS
     attention
    1.54
     time
    1.52
     Because
    1.32
     energies
    1.20
     incredible
    1.20
    Quando
    1.20
    N
    1.20
     When
    1.19
    альных
    1.16
     détruit
    1.16
    Activations Density 0.046%

    No Known Activations