© 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-RES-262K
    7. 21955
    Prev
    Next
    INDEX
    Explanations

    smart words constantly

    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_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
    linux
    0.47
     \
    0.41
    សិក
    0.41
    context
    0.40
     Education
    0.40
     denotes
    0.40
    CHAPTER
    0.39
    </h2>
    0.38
     provides
    0.38
    Linux
    0.38
    POSITIVE LOGITS
     voltaje
    0.52
     которые
    0.46
     hairstyles
    0.46
     cannons
    0.46
     cambiamenti
    0.46
     golpes
    0.46
     craziness
    0.45
     зміни
    0.45
     breech
    0.44
     расстоянии
    0.44
    Activations Density 0.001%

    No Known Activations