© 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. 206273
    Prev
    Next
    INDEX
    Explanations

    changes in

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

    levels of complexity and effort

    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
    隐藏
    0.49
    undaria
    0.47
    ز
    0.47
    Cor
    0.47
    سن
    0.46
    Vale
    0.46
    র্গ
    0.45
    ఞ
    0.45
    喿
    0.45
    сед
    0.45
    POSITIVE LOGITS
     hurriedly
    0.50
     unprofitable
    0.49
    じゃ
    0.47
     altogether
    0.46
    なくても
    0.46
     speedily
    0.46
     drastically
    0.45
    なくて
    0.45
    সম্পাদকীয়
    0.45
     pledging
    0.45
    Activations Density 0.001%

    No Known Activations