© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 91761
    Prev
    Next
    INDEX
    Explanations

    options presented by or

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

    replacing or changing specific items

    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
    рты
    0.50
     league
    0.47
    ংশ
    0.47
    rti
    0.42
     math
    0.42
     McMaster
    0.42
    ர
    0.42
    ק
    0.41
     oriente
    0.40
    math
    0.40
    POSITIVE LOGITS
     ሂደ
    0.47
    คุณภาพ
    0.46
     かわいい
    0.44
     Catawiki
    0.42
     নৃতন
    0.41
     kệ
    0.41
     বিশেষ
    0.41
     কবে
    0.40
     سٹ
    0.40
     እንዴት
    0.40
    Activations Density 0.002%

    No Known Activations