© 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. 23608
    Prev
    Next
    INDEX
    Explanations

    farmers, traders, buyers

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

    Shareholders, owners, entrepreneurs

    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
    Ethn
    0.41
    ф
    0.40
    姣
    0.40
    ⿻
    0.40
    だと
    0.39
    由
    0.38
    这家
    0.38
    出色
    0.37
    を使用した
    0.37
     distinta
    0.37
    POSITIVE LOGITS
    들에게
    0.61
    দের
    0.54
     کرام
    0.52
     चिंतित
    0.50
    কদের
    0.49
    们
    0.49
     rued
    0.45
     परेशान
    0.45
    们的
    0.45
    們
    0.44
    Activations Density 0.044%

    No Known Activations