© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220913
    Prev
    Next
    INDEX
    Explanations

    names are or `signifies` canisters

    np_acts-logits-general · gemini-2.5-flash-lite

    slavery, derogatory, offensive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     installments
    0.48
     incubation
    0.43
     عنه
    0.43
     Animations
    0.43
     مقدس
    0.42
    อด
    0.41
     postures
    0.41
     داع
    0.41
     Accepting
    0.41
    啥
    0.40
    POSITIVE LOGITS
     bushy
    0.48
     शास्त्र
    0.46
    ́c
    0.46
    concatenate
    0.46
     вирі
    0.45
    🧵
    0.45
     đình
    0.45
     বোঝার
    0.45
    商标
    0.44
    Vý
    0.44
    Activations Density 0.000%

    No Known Activations