© 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. 19239
    Prev
    Next
    INDEX
    Explanations

    large quantities and numbers

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

    large numbers and scale

    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
     Athlet
    0.50
     சேவை
    0.50
    秸
    0.49
    鹈
    0.49
     Holi
    0.47
     Wrestling
    0.47
     अनुसूचित
    0.47
     dựa
    0.47
    通风
    0.47
    猞
    0.46
    POSITIVE LOGITS
     trillions
    1.32
     billions
    1.26
     trillion
    1.04
     milliards
    1.02
     millions
    1.01
     миллиар
    0.98
     milliard
    0.96
     billion
    0.95
     billionaire
    0.94
    billion
    0.93
    Activations Density 0.035%

    No Known Activations