© 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. 256041
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pauses
    0.49
    difference
    0.48
    radiative
    0.47
     conspiracies
    0.47
    者
    0.47
    眼
    0.44
    分析
    0.42
    曝
    0.42
     Analysts
    0.41
    ෲ
    0.41
    POSITIVE LOGITS
     inglesa
    0.48
     servent
    0.47
     Abou
    0.46
     espe
    0.45
     plur
    0.45
     σύν
    0.45
    atherapy
    0.44
     crouching
    0.44
     icin
    0.44
     daug
    0.44
    Activations Density 0.001%

    No Known Activations