© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161350
    Prev
    Next
    INDEX
    Explanations

    spatial and temporal prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     മറ്റൊരു
    0.36
    xFF
    0.35
    ższ
    0.33
    Naissance
    0.33
     )\
    0.32
    NameTo
    0.30
     singularity
    0.30
     RAI
    0.30
    匹
    0.30
     लिखा
    0.29
    POSITIVE LOGITS
     around
    0.46
    around
    0.44
     beneath
    0.41
    outside
    0.41
     outside
    0.40
     पॉलिटिकल
    0.39
     rundt
    0.39
     inside
    0.39
     حول
    0.39
     बिफोर
    0.39
    Activations Density 0.032%

    No Known Activations