© 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. 179826
    Prev
    Next
    INDEX
    Explanations

    rights relating, corporate sustainability, coral gardens, mist humidifiers

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

    formation of, critical, severe, not, learning

    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
    τητας
    0.50
    त्र
    0.46
    Op
    0.45
     transcripts
    0.45
     επισ
    0.44
    Figs
    0.43
    垍
    0.43
    記者
    0.42
    ospels
    0.42
    위원회
    0.42
    POSITIVE LOGITS
     同时
    0.52
     nồi
    0.52
    но
    0.51
    arro
    0.50
     Couldn
    0.50
    unicode
    0.50
     Ginkuhà
    0.49
    েরও
    0.49
    плей
    0.49
    __."
    0.48
    Activations Density 0.000%

    No Known Activations