© 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. 58095
    Prev
    Next
    INDEX
    Explanations

    bugs and related concepts

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

    software bugs and errors

    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
     spelt
    0.47
    ⱨ
    0.47
     HOW
    0.46
     Xinhua
    0.45
    ี้ยง
    0.45
     Biblia
    0.45
     Ä
    0.45
     XVII
    0.45
     feather
    0.45
     Howe
    0.44
    POSITIVE LOGITS
     bugs
    0.94
    Bug
    0.93
    bug
    0.89
    bugs
    0.84
     Bugs
    0.80
     bug
    0.76
    🐞
    0.76
     Bug
    0.72
    BUG
    0.71
     BUG
    0.70
    Activations Density 0.013%

    No Known Activations