© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43516
    Prev
    Next
    INDEX
    Explanations

    receiving or collecting money/items

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

    The neuron fires on verbs of acquiring or receiving (like “collect,” “collected,” “collecting,” “taking,” “accepting”) when they’re used with numerical amounts.

    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
     also
    -1.71
    e
    -1.66
    h
    -1.65
    E
    -1.60
    -
    -1.60
     you
    -1.59
    ↵
    -1.55
     I
    -1.53
     {
    -1.52
    –
    -1.49
    POSITIVE LOGITS
    amkeit
    1.53
     spesso
    1.39
     liel
    1.36
     daudz
    1.35
    瑒
    1.32
    логия
    1.30
    пасибо
    1.30
    ÁG
    1.28
     menekan
    1.28
    آباد
    1.26
    Activations Density 0.073%

    No Known Activations