© 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. 178674
    Prev
    Next
    INDEX
    Explanations

    handyman, daily, festival, employers

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

    If you

    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
     stabilizes
    0.51
     ክ
    0.50
    ຄວ
    0.49
     láser
    0.49
    ương
    0.48
    າມາດ
    0.48
    ຕິດຕໍ່
    0.48
     restricts
    0.47
     rectify
    0.47
     sukham
    0.47
    POSITIVE LOGITS
    ม
    0.51
    ت
    0.49
    ことを
    0.48
    ก
    0.47
    Host
    0.46
    🇩
    0.46
    LA
    0.46
    ر
    0.46
    administration
    0.46
    O
    0.46
    Activations Density 0.000%

    No Known Activations