© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50442
    Prev
    Next
    INDEX
    Explanations

    bogged down / weighed down / gusty / rained out

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

    stuck or glitching

    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
     將
    0.52
     woodwork
    0.50
     ইহাদের
    0.50
     meson
    0.49
     poplar
    0.49
     sandalwood
    0.48
     elucidation
    0.48
     första
    0.47
     noten
    0.47
     これは
    0.47
    POSITIVE LOGITS
    בה
    0.54
     परेशानियों
    0.52
     overkill
    0.52
    -
    0.47
    一样
    0.47
    С
    0.47
    ба
    0.46
    రిగి
    0.46
    不一样
    0.46
    变成了
    0.46
    Activations Density 0.009%

    No Known Activations