© 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. 180147
    Prev
    Next
    INDEX
    Explanations

    special characters and specific words

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

    disable root motion

    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
     fraudulent
    0.50
     horrendous
    0.49
     prostitutes
    0.47
     bogus
    0.47
     чтоб
    0.45
     fraudulently
    0.45
     drawRight
    0.45
     slimy
    0.44
     aby
    0.44
     ہ
    0.44
    POSITIVE LOGITS
    ée
    0.50
    wellness
    0.49
    fi
    0.45
    ōu
    0.45
     unapolog
    0.44
    餐饮
    0.43
    ées
    0.42
    新能源
    0.42
    âm
    0.42
    াও
    0.41
    Activations Density 0.001%

    No Known Activations