© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14680
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and rankings

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

    first occurrence "loss" or "reaction"

    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
    针对
    0.27
    。“
    0.25
    。”
    0.25
    requires
    0.24
    这时
    0.24
    。
    0.23
    ；
    0.23
    Coor
    0.23
    িল্প
    0.23
    随着
    0.23
    POSITIVE LOGITS
     hech
    0.34
     hany
    0.34
     Mbappe
    0.34
     manifestly
    0.33
     அவர்
    0.33
     conseiller
    0.33
    というか
    0.32
     ന
    0.32
     nejen
    0.32
     じゃん
    0.32
    Activations Density 0.000%

    No Known Activations