© 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. 56517
    Prev
    Next
    INDEX
    Explanations

    adjective + noun phrases

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

    words ending in 'ative'

    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
    ಮ
    0.84
    在
    0.82
    ール
    0.75
    या
    0.73
    自己的
    0.72
    R
    0.72
    전
    0.71
    kých
    0.70
    ために
    0.70
    L
    0.70
    POSITIVE LOGITS
    ௭
    0.67
     resuscitation
    0.65
    лна
    0.63
    )
    0.63
    itys
    0.62
    ine
    0.61
    ವಾಗಿ
    0.61
     not
    0.61
    il
    0.59
    стом
    0.58
    Activations Density 0.286%

    No Known Activations