© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30679
    Prev
    Next
    INDEX
    Explanations

    qualifying and exclusive phrases

    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
    ཱ
    0.47
    恋爱
    0.45
     обуча
    0.45
    itiveness
    0.45
     શકે
    0.44
     изделия
    0.44
     तलाश
    0.44
     설립
    0.44
    ക്ട
    0.43
    acariy
    0.43
    POSITIVE LOGITS
     capillaries
    0.46
     ursprüng
    0.45
     longueur
    0.45
     setae
    0.45
     tường
    0.45
    用
    0.45
     using
    0.45
     hairs
    0.44
     on
    0.44
     pomocí
    0.43
    Activations Density 0.010%

    No Known Activations