© 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. 41-GEMMASCOPE-2-RES-262K
    7. 62776
    Prev
    Next
    INDEX
    Explanations

    microfinance and micro-loans

    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_all/layer_41_width_262k_l0_big
    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
     horns
    0.38
     Mackenzie
    0.38
    typing
    0.37
    Dot
    0.37
     درجه
    0.37
    PointerException
    0.36
    喷
    0.35
     nn
    0.35
    Jamie
    0.35
    ු
    0.35
    POSITIVE LOGITS
     micro
    0.89
     Gr
    0.79
     микро
    0.78
     Micro
    0.78
     microl
    0.77
    micro
    0.74
     mikro
    0.73
     Yun
    0.73
    Micro
    0.72
    微
    0.70
    Activations Density 0.002%

    No Known Activations