© 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. 222938
    Prev
    Next
    INDEX
    Explanations

    level details

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

    add, actively, trying

    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
    with
    0.57
    复制
    0.51
    以下
    0.45
     eliminated
    0.45
     accompanied
    0.44
     with
    0.43
    ================
    0.43
    时间
    0.43
     undergoing
    0.43
     Keyboard
    0.43
    POSITIVE LOGITS
    ਾਰ
    0.53
    ೋಟ
    0.51
     হলুদ
    0.48
    ಾನು
    0.46
     ஊற
    0.46
    賄
    0.45
     еле
    0.45
     겨울
    0.45
     chicago
    0.44
    जरी
    0.43
    Activations Density 0.000%

    No Known Activations