© 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. 105733
    Prev
    Next
    INDEX
    Explanations

    magic phrases and concepts

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

    basic information

    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
    வதை
    0.51
    á
    0.50
    ่า
    0.47
    éph
    0.45
    ཆ
    0.45
     Sexton
    0.45
     दिखाना
    0.45
    एप
    0.44
    ẹ̀
    0.44
    ీ
    0.44
    POSITIVE LOGITS
    如下
    0.47
    trap
    0.46
    speaker
    0.44
     Populations
    0.44
     trol
    0.43
     普通
    0.43
     descendants
    0.42
     জনসংখ্যার
    0.40
    ng
    0.40
     rumah
    0.40
    Activations Density 0.011%

    No Known Activations