© 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. 260650
    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
    Excerpt
    0.44
    鰱
    0.43
    ی
    0.41
    어가
    0.40
    われた
    0.40
    excerpt
    0.40
     WorldCat
    0.39
    с
    0.39
    鱻
    0.39
    자의
    0.39
    POSITIVE LOGITS
     drifted
    0.49
     infring
    0.48
     compatibles
    0.46
     împ
    0.45
     透明
    0.45
    ืน
    0.43
     sockets
    0.43
     breached
    0.42
     kompat
    0.42
     drones
    0.42
    Activations Density 0.000%

    No Known Activations