© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39081
    Prev
    Next
    INDEX
    Explanations

    mass production

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

    mass displacement movements media

    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
     to
    0.60
     a
    0.52
     lī
    0.51
    ł
    0.50
    ниш
    0.49
    مک
    0.47
     związku
    0.47
    م
    0.47
    بین
    0.47
     streaks
    0.47
    POSITIVE LOGITS
     mass
    1.13
     массо
    0.96
     bulk
    0.95
    mass
    0.86
    bulk
    0.84
    批量
    0.78
     Mass
    0.77
     Bulk
    0.76
     masses
    0.76
    Bulk
    0.76
    Activations Density 0.040%

    No Known Activations