© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12515
    Prev
    Next
    INDEX
    Explanations

    investing and lending money

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

    The neuron activates strongly on occurrences of the word “invest” (and its forms such as “investing,” “investments,” etc.), i.e. it detects investment-related verbs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oper
    0.56
    Oper
    0.55
    pet
    0.54
    äter
    0.54
    átku
    0.53
    >}</
    0.53
     opat
    0.52
     Petro
    0.49
    DrawerToggle
    0.49
     Nab
    0.49
    POSITIVE LOGITS
     credibility
    0.60
     displaying
    0.56
    ısınız
    0.55
     이제
    0.55
    సక్తి
    0.54
    ?!"
    0.54
     SHOULD
    0.53
     प्रदर्शित
    0.53
    !!!"
    0.52
    痱
    0.52
    Activations Density 0.000%

    No Known Activations