© 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. 78390
    Prev
    Next
    INDEX
    Explanations

    funding cuts and budgetary reductions

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

    drug costs, healthcare, and budgets

    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
    🥰
    0.44
     తాజాగా
    0.43
     uncond
    0.41
    ccncc
    0.41
     🥰
    0.39
    袤
    0.39
     excitations
    0.39
    占用
    0.39
    🗿
    0.39
    主演
    0.38
    POSITIVE LOGITS
     budgets
    0.49
     финанси
    0.47
     funding
    0.46
     যদি
    0.46
    ಂಟ
    0.46
     impost
    0.46
     finanzi
    0.45
     keuangan
    0.44
     אם
    0.44
     budgetary
    0.44
    Activations Density 0.000%

    No Known Activations