© 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. 69235
    Prev
    Next
    INDEX
    Explanations

    group stellar mass, stuff in, led by

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

    start or middle initiators

    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
    usa
    0.42
     পরিণ
    0.42
     ezingu
    0.41
    楽
    0.41
    umi
    0.41
    USA
    0.40
     dịp
    0.40
    URY
    0.40
     acara
    0.39
     destacados
    0.39
    POSITIVE LOGITS
     Система
    0.50
    З
    0.48
    欬
    0.45
    фектив
    0.45
    gget
    0.44
     Ло
    0.44
    Ло
    0.44
    нент
    0.44
    ческие
    0.43
    ఖా
    0.43
    Activations Density 0.004%

    No Known Activations