© 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. 2737
    Prev
    Next
    INDEX
    Explanations

    worldwide growth and numbers

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

    growth and active communities

    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
     প্রত্যাহার
    0.48
    ผ้า
    0.46
     minimalistic
    0.45
    Reset
    0.45
    😰
    0.45
    immutable
    0.44
    食事
    0.44
    特定的
    0.43
    ᱷ
    0.43
    Immutable
    0.43
    POSITIVE LOGITS
     prolifer
    0.80
     worldwide
    0.77
     تعداد
    0.75
     nationwide
    0.70
     weltweit
    0.69
    全国
    0.68
     enthusiasts
    0.67
    全國
    0.64
     proliferating
    0.64
     Worldwide
    0.63
    Activations Density 0.165%

    No Known Activations