© 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. 111153
    Prev
    Next
    INDEX
    Explanations

    family sat

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

    display results or announcements

    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
     fluctu
    0.55
     bahsede
    0.50
     vaste
    0.49
     beset
    0.47
     swelled
    0.46
     mortgage
    0.45
     defect
    0.44
    ኾ
    0.44
     salary
    0.43
     развитие
    0.43
    POSITIVE LOGITS
    Adapt
    0.49
     Jahrhund
    0.48
    মধ
    0.48
    HOUR
    0.48
    Hour
    0.48
    菁
    0.47
    浊
    0.47
    啍
    0.47
    ਕ
    0.46
     enviados
    0.46
    Activations Density 0.001%

    No Known Activations