© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 62528
    Prev
    Next
    INDEX
    Explanations

    sagging, sinking, settling, dip

    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
    リーチ
    0.41
     terminated
    0.41
     hybrid
    0.40
     Br
    0.38
     exploded
    0.38
    athery
    0.38
    粙
    0.38
     detachable
    0.38
     Reach
    0.37
    "));
    0.37
    POSITIVE LOGITS
     sinking
    1.39
     subsidence
    1.29
     sink
    1.18
     sinks
    1.16
    Sink
    1.13
    sink
    1.09
     Sink
    1.09
     sank
    1.08
    沉
    1.08
     sagging
    1.05
    Activations Density 0.003%

    No Known Activations