© 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. 5710
    Prev
    Next
    INDEX
    Explanations

    event before a transition

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

    indicates a temporal sequence

    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
    の
    0.34
    ۔
    0.29
     WHEN
    0.26
     ketika
    0.25
     ilə
    0.25
     これは
    0.25
    0.25
     itr
    0.24
     これ
    0.24
     cuando
    0.24
    POSITIVE LOGITS
    i
    0.29
    being
    0.28
    g
    0.25
    x
    0.25
    <0xA1>
    0.24
    having
    0.24
    有着
    0.24
    xi
    0.24
    sti
    0.24
    present
    0.23
    Activations Density 0.212%

    No Known Activations