© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 525
    Prev
    Next
    INDEX
    Explanations

    large numbers and units like million

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     naal
    1.11
    ذن
    1.08
    态
    1.04
     вниз
    1.04
    反対
    1.03
     правой
    1.03
    受け
    1.02
    Enders
    1.00
    恥
    1.00
    otrans
    1.00
    POSITIVE LOGITS
     lakh
    2.19
     thousand
    2.13
     million
    2.07
     Million
    2.03
    million
    2.01
     lakhs
    1.99
     millón
    1.94
     millions
    1.92
    Million
    1.92
     thousands
    1.91
    Activations Density 1.945%

    No Known Activations