© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 5353
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by articles

    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
    ैर्य
    0.47
     quienes
    0.44
     fosters
    0.44
     argues
    0.43
    ᐋ
    0.43
     Eğer
    0.43
    にて
    0.42
     والتي
    0.42
     As
    0.42
     także
    0.41
    POSITIVE LOGITS
    '_{
    0.41
     '+'
    0.40
    ്യത
    0.39
     IOException
    0.39
    itaire
    0.39
     häufig
    0.38
     různ
    0.38
    ⭐
    0.38
    🤷
    0.38
    corona
    0.37
    Activations Density 0.022%

    No Known Activations