© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    control, subtropical, throughput

    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
    ďaka
    0.42
     cuja
    0.41
    ությ
    0.40
     بتاعتنا
    0.39
    탉
    0.38
    kipun
    0.37
     cliquant
    0.37
    См
    0.36
    whose
    0.36
    𒁕
    0.36
    POSITIVE LOGITS
     katika
    1.02
     ở
    0.96
    នៅក្នុង
    0.91
     trên
    0.90
     în
    0.83
     across
    0.83
     في
    0.82
     in
    0.81
     on
    0.81
     kwenye
    0.81
    Activations Density 0.219%

    No Known Activations