© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 167
    Prev
    Next
    INDEX
    Explanations

    harm or copies is/was

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

    The neuron fires on terms related to financial or economic activity (e.g. investments, capital, growth, ventures).

    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
     sélectionnez
    0.42
     sofre
    0.37
     돼요
    0.37
    Ꮇ
    0.36
     হইত
    0.36
     choisissez
    0.36
     ہوتے
    0.35
     pensato
    0.35
    ᔕ
    0.35
     recouvert
    0.35
    POSITIVE LOGITS
     precludes
    0.74
     prompted
    0.71
     outweighs
    0.68
     culminated
    0.67
     compels
    0.65
     spurred
    0.64
     culminates
    0.64
     led
    0.63
     makes
    0.62
     stems
    0.61
    Activations Density 0.555%

    No Known Activations