© 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. 40-GEMMASCOPE-2-RES-262K
    4. 6408
    Prev
    Next
    INDEX
    Explanations

    prepositions and 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_40_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
     ,
    0.23
     or
    0.19
    ↵
    0.18
     and
    0.18
     ;
    0.17
     ...,
    0.17
    0
    0.17
     gleichen
    0.16
     Increase
    0.16
    म
    0.16
    POSITIVE LOGITS
     being
    0.32
     what
    0.29
     having
    0.29
     быть
    0.29
     how
    0.27
     why
    0.26
     bagaimana
    0.26
     activism
    0.25
    having
    0.25
     skepticism
    0.25
    Activations Density 0.373%

    No Known Activations