© 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-262K
    7. 31970
    Prev
    Next
    INDEX
    Explanations

    cooking class or recessed keyboard

    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_262k_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
    的服务
    0.40
    目的是
    0.38
     ٹرسٹ
    0.37
    녓
    0.37
     abordagem
    0.37
    녕
    0.36
    配套
    0.36
    ක්‍
    0.36
    flage
    0.35
    unches
    0.35
    POSITIVE LOGITS
    u
    0.51
    q
    0.47
     orthogon
    0.44
    લ
    0.44
    itude
    0.43
    0
    0.43
    ==
    0.42
    хии
    0.42
     দেখে
    0.41
    ଜ
    0.41
    Activations Density 0.000%

    No Known Activations