© 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. 7101
    Prev
    Next
    INDEX
    Explanations

    I, we, they statements

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

    doing things I can

    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
    这是一个
    0.22
    这
    0.21
    由于
    0.20
    是一个
    0.20
     strikeouts
    0.20
     เปลี่ยน
    0.20
    就是一个
    0.20
    தியின்
    0.19
    သောအ
    0.19
    它
    0.19
    POSITIVE LOGITS
     gebruiken
    0.25
    gger
    0.22
    挀
    0.19
     пыта
    0.18
     impulsar
    0.18
     cotidian
    0.18
     inev
    0.18
    джер
    0.18
     считают
    0.18
     inad
    0.17
    Activations Density 0.853%

    No Known Activations