© 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. 64352
    Prev
    Next
    INDEX
    Explanations

    compacting, symbol of, further comprising, cooperation with

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

    compact, releasing hormones, particularly vulnerable

    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
     preferring
    0.46
    cs
    0.43
    一个小
    0.43
    "></
    0.42
     আসন্ন
    0.41
    x
    0.41
    പ്പെട്ടി
    0.40
    രാജ
    0.40
    Guard
    0.39
     match
    0.39
    POSITIVE LOGITS
     الوز
    0.47
    怎麼
    0.47
    ﺪ
    0.46
    ıml
    0.46
     değişken
    0.45
     व्
    0.44
    اران
    0.43
    ثمان
    0.43
     записа
    0.43
    how
    0.43
    Activations Density 0.000%

    No Known Activations