© 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. 45796
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    year-month-day numbers

    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
     pleases
    0.48
    ้ม
    0.45
    jeni
    0.42
    Пред
    0.42
    riech
    0.41
    เชื่อ
    0.41
    তিনি
    0.40
    ﭥ
    0.40
    ربي
    0.39
     znač
    0.39
    POSITIVE LOGITS
     noon
    0.43
     ν
    0.42
     SalesLT
    0.41
     uur
    0.39
     UUID
    0.39
     t
    0.38
     Expressions
    0.38
    𝕟
    0.38
     Query
    0.38
     Morning
    0.38
    Activations Density 0.009%

    No Known Activations