© 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. 63836
    Prev
    Next
    INDEX
    Explanations

    harmless or toxic

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

    biocompatible and safe

    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
    Not in Any Lists

    No Comments

    Negative Logits
    FUNCTION
    0.45
    Chevrolet
    0.44
    融合
    0.43
     ত্রি
    0.43
     ሥራ
    0.42
    reichen
    0.41
    িমে
    0.41
    摇
    0.41
    лектро
    0.41
     গাড়ি
    0.41
    POSITIVE LOGITS
     harmless
    0.84
     toxicity
    0.78
     toxic
    0.75
     biocompat
    0.74
     toxins
    0.71
    toxic
    0.71
    toxicity
    0.68
     безопас
    0.68
     Toxicity
    0.68
     safe
    0.67
    Activations Density 0.155%

    No Known Activations