© 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. 10666
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
     这个
    0.29
    ları
    0.28
     让
    0.28
    读取
    0.28
    诞
    0.28
    愀
    0.28
    Input
    0.27
    代码
    0.27
    节点
    0.27
    ıları
    0.27
    POSITIVE LOGITS
     legitim
    0.28
     health
    0.26
     foci
    0.26
    *}$
    0.26
     candid
    0.25
     gestion
    0.25
     salut
    0.25
     Sicherheits
    0.25
     demain
    0.25
     Spitzen
    0.25
    Activations Density 0.090%

    No Known Activations