© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7524
    Prev
    Next
    INDEX
    Explanations

    code slicing and indexing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    有一個
    0.25
    -">
    0.23
    Plaintiff
    0.22
    vertine
    0.22
    [{}\
    0.22
    ریٹر
    0.22
    aspetto
    0.21
    erder
    0.21
    Smith
    0.21
    Введите
    0.21
    POSITIVE LOGITS
    +
    0.25
     +
    0.23
     Seniors
    0.23
     ভো
    0.22
    也会
    0.22
     toca
    0.22
     plusieurs
    0.21
     también
    0.21
     principales
    0.21
    க்கு
    0.20
    Activations Density 0.145%

    No Known Activations