© 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. 32917
    Prev
    Next
    INDEX
    Explanations

    passed or beyond

    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
    ້ອ
    0.36
    acetamide
    0.36
     (;
    0.34
     foreground
    0.34
    кты
    0.34
     Masks
    0.34
    трибу
    0.33
    현
    0.33
     തവണ
    0.33
     Foreground
    0.33
    POSITIVE LOGITS
     passed
    1.54
     beyond
    1.48
     past
    1.46
    passed
    1.43
     pasado
    1.33
     지나
    1.32
    beyond
    1.31
    Beyond
    1.30
    過了
    1.30
    Passed
    1.30
    Activations Density 0.002%

    No Known Activations