© 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. 40-GEMMASCOPE-2-RES-262K
    7. 192068
    Prev
    Next
    INDEX
    Explanations

    Arizona, file, text properties

    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
    Negative Logits
     }>
    0.40
     Desert
    0.40
     McCr
    0.38
    ബരി
    0.38
     McDowell
    0.38
    Desert
    0.38
     Opera
    0.37
    ellos
    0.37
    icer
    0.37
    Opera
    0.37
    POSITIVE LOGITS
     bestimmen
    0.41
    vk
    0.40
    炼
    0.39
     stre
    0.38
    軚
    0.38
    team
    0.38
     bourgeoisie
    0.37
    /-
    0.37
    森
    0.37
    🤑
    0.36
    Activations Density 0.003%

    No Known Activations