© 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. 6636
    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
    ید
    0.19
    رحمن
    0.17
    पोज
    0.17
    yorum
    0.17
     mjesto
    0.16
     yönt
    0.16
     upang
    0.16
    虾
    0.15
     Öncelikle
    0.15
     mwen
    0.15
    POSITIVE LOGITS
     and
    0.22
     any
    0.22
     all
    0.22
     những
    0.22
     thousands
    0.21
     hundreds
    0.21
     large
    0.21
     các
    0.20
     모든
    0.20
     many
    0.20
    Activations Density 1.984%

    No Known Activations