© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8299
    Prev
    Next
    INDEX
    Explanations

    positive descriptive adjectives

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

    describing positive qualities followed by nouns

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sumptuous
    0.56
     enviable
    0.56
     tasteful
    0.55
    优质
    0.53
     চমৎকার
    0.53
    或
    0.53
     அழகான
    0.53
    优秀的
    0.53
     enthusiastic
    0.52
    ຫຼື
    0.52
    POSITIVE LOGITS
     duo
    0.48
     yet
    0.45
     tiered
    0.45
     additions
    0.45
     KER
    0.44
     LK
    0.43
     KDE
    0.42
     ترین
    0.42
     K
    0.41
     KE
    0.40
    Activations Density 0.428%

    No Known Activations