© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    blockage or clogging

    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
     salaried
    0.51
    ើន
    0.48
    ្វ
    0.47
    េះ
    0.47
    ෲ
    0.47
    ّر
    0.46
     symmetric
    0.46
     répartition
    0.45
     antisymmetric
    0.44
    ُم
    0.44
    POSITIVE LOGITS
     clogged
    2.05
     clogging
    2.03
     clog
    2.02
     blockage
    1.87
     blocked
    1.75
    堵
    1.59
    blocked
    1.51
    Blocked
    1.46
     blocking
    1.42
     obstru
    1.41
    Activations Density 0.012%

    No Known Activations