© 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. 60980
    Prev
    Next
    INDEX
    Explanations

    actionable concepts

    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
    ץ
    0.46
     you
    0.46
    spaper
    0.45
     my
    0.45
     everyone
    0.45
     t
    0.44
    )
    0.41
     stolen
    0.40
    Ç
    0.40
     in
    0.39
    POSITIVE LOGITS
    atás
    0.52
     généralement
    0.50
     đang
    0.50
     peux
    0.46
     empê
    0.45
     válida
    0.45
    權
    0.45
     സമ
    0.45
    が多い
    0.44
     உதாரணமாக
    0.44
    Activations Density 0.005%

    No Known Activations