© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    regulatory and financial topics

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

    The neuron fires on standalone, high‐level financial or policy nouns—terms like “insurance,” “tax,” “budget,” “ratings,” “GDP,” 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
     Bootstrap
    0.75
    性和
    0.75
    and
    0.75
     &/
    0.75
    CreateParams
    0.73
    LL
    0.73
    SYN
    0.73
    the
    0.72
    T
    0.72
    AND
    0.71
    POSITIVE LOGITS
     deoarece
    1.02
     internacionales
    0.87
     είχε
    0.86
     situación
    0.79
     ponieważ
    0.79
     refinancing
    0.77
     keuangan
    0.76
     changé
    0.75
    耋
    0.75
     annuity
    0.75
    Activations Density 0.002%

    No Known Activations