© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1920
    Prev
    Next
    INDEX
    Explanations

    industry sectors and their related activities

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

    The neuron fires strongly on commercial and industry contexts—that is, mentions of businesses, markets, products, services, or industry‐related terms.

    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_24_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
    ገኙ
    0.50
    Ont
    0.48
    前半
    0.47
     일
    0.47
    ക്കെ
    0.47
    できた
    0.47
     Confederate
    0.46
     ਟ
    0.45
     Nat
    0.44
     Trần
    0.44
    POSITIVE LOGITS
     or
    0.82
     или
    0.78
     അല്ലെങ്കിൽ
    0.76
     eller
    0.70
    或
    0.69
     หรือ
    0.68
     atau
    0.67
     அல்லது
    0.66
     hoặc
    0.66
     ወይም
    0.65
    Activations Density 0.037%

    No Known Activations