© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9903
    Prev
    Next
    INDEX
    Explanations

    quantities after 'than'

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

    large numerical quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     ఒక
    0.54
     dwóch
    0.54
     প্রেমের
    0.52
     δύο
    0.50
     ühe
    0.50
     خبری
    0.46
     jednego
    0.46
    茈
    0.45
     שני
    0.45
     antiserum
    0.44
    POSITIVE LOGITS
     millions
    0.75
    illions
    0.71
     trillions
    0.70
    illion
    0.67
     billions
    0.66
    Millions
    0.63
     trillion
    0.63
     milioane
    0.63
     thousands
    0.62
     Millions
    0.62
    Activations Density 0.071%

    No Known Activations