© 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. 6220
    Prev
    Next
    INDEX
    Explanations

    discount rate and future value

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

    This neuron detects section headings or structured list items (e.g., table‐of‐contents entries and title lines) in a document.

    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
     rates
    0.68
     porcent
    0.68
    rates
    0.66
     सीतारमण
    0.65
     Rate
    0.65
     Rates
    0.64
    率は
    0.63
     ล
    0.62
     मिल्क
    0.61
    率
    0.61
    POSITIVE LOGITS
    社会
    0.54
    Influence
    0.52
    ABA
    0.51
    社會
    0.50
     corrobor
    0.50
    ATTA
    0.50
     Versus
    0.50
     официа
    0.49
     Kontext
    0.49
     sociale
    0.48
    Activations Density 0.000%

    No Known Activations