© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12342
    Prev
    Next
    INDEX
    Explanations

    market business strategy

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

    The neuron fires on nouns that denote commercial or professional concepts (like production, business, price, experience, release, application, etc.).

    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
    .
    0.68
    বর্তী
    0.57
    liu
    0.53
    )
    0.51
    mouseleave
    0.51
    が変わ
    0.51
    mselves
    0.51
    ;
    0.50
    ซ์
    0.47
    വരുടെ
    0.47
    POSITIVE LOGITS
     trois
    0.57
    DIV
    0.54
     splurge
    0.54
     DIV
    0.53
    MPC
    0.52
    𒊹
    0.52
     três
    0.51
     трёх
    0.51
    SPC
    0.50
     كا
    0.50
    Activations Density 0.000%

    No Known Activations