© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15131
    Prev
    Next
    INDEX
    Explanations

    time periods and durations

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

    common choice or understanding

    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
    시간
    0.37
    хи
    0.36
    Д
    0.36
    ми
    0.36
    я
    0.36
    жи
    0.35
    ве
    0.34
    К
    0.34
    ка
    0.34
    лан
    0.33
    POSITIVE LOGITS
     删除
    0.34
     findViewById
    0.32
     bijective
    0.32
     phosphorylated
    0.32
     ϕ
    0.32
     symmet
    0.31
     "\\"
    0.30
     suppressing
    0.30
     "%
    0.30
     获取
    0.30
    Activations Density 0.037%

    No Known Activations