© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31288
    Prev
    Next
    INDEX
    Explanations

    eras and movements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     प्राचीन
    0.55
    Ancient
    0.55
    ancient
    0.52
     ancient
    0.50
     древ
    0.48
    古代
    0.47
     古
    0.47
    古
    0.47
     archaic
    0.45
     Ancient
    0.45
    POSITIVE LOGITS
     postmodern
    0.90
     neoliberal
    0.76
     genomics
    0.70
     modernas
    0.70
     modernos
    0.68
     globalization
    0.68
     grunge
    0.66
     biotech
    0.65
    近年
    0.65
     Obamacare
    0.65
    Activations Density 0.030%

    No Known Activations