© 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. 259626
    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
    Exercise
    0.57
    س
    0.51
    सम्
    0.50
    ває
    0.49
    莎
    0.49
    ন্‌
    0.47
    ສົ
    0.46
    ن
    0.46
    遂
    0.46
    ადა
    0.46
    POSITIVE LOGITS
     methylene
    0.50
     kiosk
    0.46
     midi
    0.43
     leaflet
    0.43
    엽
    0.43
     Flücht
    0.42
     monoch
    0.42
     emblematic
    0.42
     cafeteria
    0.42
    똘
    0.41
    Activations Density 0.001%

    No Known Activations