© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83009
    Prev
    Next
    INDEX
    Explanations

    so, therefore, and

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

    understand the concept

    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
    缁
    0.46
    सर्जन
    0.44
     duration
    0.43
     Tulane
    0.43
     dea
    0.41
     клеток
    0.41
    াজন
    0.41
    FolderPath
    0.40
    哿
    0.40
     licensee
    0.39
    POSITIVE LOGITS
     個人
    0.53
     お
    0.51
    バター
    0.49
    oj
    0.48
     手
    0.47
     기본적인
    0.46
    ohon
    0.46
    ob
    0.46
     ウェ
    0.46
     取り
    0.45
    Activations Density 0.001%

    No Known Activations