© 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-65K
    7. 52564
    Prev
    Next
    INDEX
    Explanations

    Rs. or fake

    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
    Negative Logits
     feitas
    0.50
     suivantes
    0.47
     sway
    0.47
     concierge
    0.46
    イ
    0.45
     hold
    0.45
     teatro
    0.45
     beams
    0.44
     ainfi
    0.44
     sams
    0.43
    POSITIVE LOGITS
    PickerDialog
    0.43
     %>',
    0.42
    arabangsa
    0.42
     নীচে
    0.41
    BottomSheet
    0.41
     بما
    0.39
    SSE
    0.39
     تحت
    0.38
    Violation
    0.38
     স্বাধীনতা
    0.37
    Activations Density 0.010%

    No Known Activations