© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 160918
    Prev
    Next
    INDEX
    Explanations

    for a

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

    Qing Dynasty

    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
    淳
    0.49
    ผสม
    0.47
     綿
    0.46
    ジャ
    0.46
     ジャ
    0.45
     使い
    0.45
    ící
    0.44
    }{}
    0.44
    のない
    0.43
     defy
    0.43
    POSITIVE LOGITS
    িনবার্গ
    0.47
    ارى
    0.46
     wherever
    0.40
    internal
    0.39
     Incoming
    0.39
    Yang
    0.38
    ADDR
    0.38
    ുമെന്ന്
    0.38
    anath
    0.37
     ylim
    0.37
    Activations Density 0.001%

    No Known Activations