© 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-16K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    years, months, periods

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

    periods and processes

    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_16k_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
    早在
    0.55
    最近
    0.54
    現在は
    0.52
     zuletzt
    0.51
    recent
    0.51
     when
    0.50
     quando
    0.50
    앉
    0.50
     오래
    0.50
     όταν
    0.50
    POSITIVE LOGITS
     कई
    0.62
    陆续
    0.58
     നിരവധി
    0.54
     ocur
    0.53
    何度も
    0.53
     gradually
    0.52
    发生了
    0.52
    的过程中
    0.52
    不断
    0.51
     accumulate
    0.51
    Activations Density 0.281%

    No Known Activations