© 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. 33971
    Prev
    Next
    INDEX
    Explanations

    modern, contemporary, new

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

    modern and recent updates

    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
    先前
    0.43
    此前
    0.41
    ก่อน
    0.38
     voordat
    0.38
    antes
    0.37
    ⃖
    0.37
     vorticity
    0.37
     étamines
    0.37
     prevState
    0.36
    醞
    0.36
    POSITIVE LOGITS
     modern
    2.36
    现代
    2.22
     आधुनिक
    2.17
    現代
    2.17
     moderne
    2.13
    modern
    2.11
     modernos
    2.09
     современные
    2.09
     moderno
    2.08
     современ
    2.06
    Activations Density 0.285%

    No Known Activations