© 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. 90858
    Prev
    Next
    INDEX
    Explanations

    predicted line, global online, but neither

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

    quality and comparison

    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
    Negative Logits
    ୀ
    0.47
     позволит
    0.47
    ୈ
    0.46
     Ingeniería
    0.46
    accordo
    0.44
    ικό
    0.43
     समझौते
    0.43
    痺
    0.43
    𝒋
    0.43
     άλ
    0.42
    POSITIVE LOGITS
    igenschaften
    0.51
     produse
    0.50
     miserably
    0.50
     agh
    0.49
     wretched
    0.49
     superior
    0.48
     haute
    0.48
     fickle
    0.48
     laut
    0.47
    脸色
    0.47
    Activations Density 0.006%

    No Known Activations