© 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. 37834
    Prev
    Next
    INDEX
    Explanations

    economic stimulus and recovery acts

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

    government stimulus and legislation

    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
     jährlich
    0.54
    每年
    0.53
    俪
    0.47
     Biochim
    0.47
     jähr
    0.47
     सालाना
    0.46
    Bechyné
    0.46
    实验室
    0.46
    Neuro
    0.46
    严
    0.46
    POSITIVE LOGITS
     trillions
    0.58
     payroll
    0.57
     forgive
    0.57
     forg
    0.57
     forgiveness
    0.55
     stimulus
    0.54
     payouts
    0.54
     billions
    0.53
     furlough
    0.53
     forgiven
    0.52
    Activations Density 0.020%

    No Known Activations