© 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. 53446
    Prev
    Next
    INDEX
    Explanations

    concept, not, even, description

    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
    ফার
    0.46
    平
    0.43
    }}^{\
    0.42
    结
    0.42
    isak
    0.39
    碘
    0.39
    何
    0.39
    jetbrains
    0.38
    Philadelphia
    0.38
    灰
    0.38
    POSITIVE LOGITS
     tolerable
    0.48
     делу
    0.45
     सोचा
    0.44
     yılları
    0.43
     dimly
    0.43
    発売
    0.43
     こちら
    0.43
    čili
    0.42
     sarebbe
    0.42
    üsü
    0.42
    Activations Density 0.002%

    No Known Activations