© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 1924
    Prev
    Next
    INDEX
    Explanations

    when followed by clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     পারলে
    0.50
     therefrom
    0.44
    นักงาน
    0.43
    យៈ
    0.42
     aussitôt
    0.42
    тріш
    0.41
    <unused693>
    0.39
    źć
    0.38
     thermoplastic
    0.38
    परेशन
    0.37
    POSITIVE LOGITS
     when
    1.73
     هنگام
    1.67
     prilikom
    1.64
    when
    1.55
     lors
    1.48
     cuando
    1.46
     أثناء
    1.44
     när
    1.43
     когда
    1.40
     quando
    1.39
    Activations Density 0.004%

    No Known Activations