© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13854
    Prev
    Next
    INDEX
    Explanations

    fundraising for causes

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

    The neuron activates on mentions of fundraising or charitable giving—especially when highlighting donations, proceeds, benefits, or amounts raised.

    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
    {?>
    -1.41
     køb
    -1.35
     некоторых
    -1.35
     =>{
    -1.27
     there
    -1.27
    嗚
    -1.27
     épaules
    -1.24
     first
    -1.22
     here
    -1.20
    日で
    -1.20
    POSITIVE LOGITS
    絶対に
    1.30
    一応
    1.30
     τῶν
    1.25
     என்று
    1.24
     отличается
    1.20
     vraiment
    1.19
    ја
    1.19
    诋
    1.18
    re
    1.17
     sob
    1.15
    Activations Density 0.026%

    No Known Activations