© 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. 257423
    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
    ี้
    0.50
    肄
    0.48
     قدر
    0.46
    电设备
    0.46
     gacche
    0.46
    懺
    0.46
    ulare
    0.45
    nungs
    0.45
    ไลน์
    0.44
     ভুগ
    0.43
    POSITIVE LOGITS
    B
    0.60
    K
    0.59
    M
    0.55
    W
    0.53
    Pod
    0.52
    F
    0.50
    Though
    0.50
    X
    0.50
    Hlav
    0.49
    El
    0.49
    Activations Density 0.001%

    No Known Activations