© 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. 259279
    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
     captioned
    0.50
     بالضبط
    0.46
    業者
    0.46
     Quentin
    0.45
     بوص
    0.45
    誇
    0.45
     Carrie
    0.44
     پروف
    0.44
     امریکا
    0.44
     సో
    0.43
    POSITIVE LOGITS
     Till
    0.47
    os
    0.46
    ↓
    0.45
     findet
    0.44
    M
    0.44
    द्री
    0.43
     fique
    0.42
    Incre
    0.42
    Ме
    0.42
     Methods
    0.41
    Activations Density 0.000%

    No Known Activations