© 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. 260851
    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
    នាំ
    0.51
    房价
    0.49
    を中心に
    0.49
    竝
    0.48
    滤波器
    0.47
    minecraft
    0.47
    京东
    0.45
    fänger
    0.44
    鉉
    0.44
     موبائل
    0.43
    POSITIVE LOGITS
     called
    0.68
     accompanied
    0.61
     at
    0.57
     of
    0.55
     entitled
    0.54
     injure
    0.54
     set
    0.54
     clutter
    0.54
     left
    0.53
     bew
    0.52
    Activations Density 0.000%

    No Known Activations