© 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. 253821
    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
    pora
    0.42
     Himalaya
    0.42
    unca
    0.41
    plicity
    0.41
     👉
    0.41
     النج
    0.40
     diantaranya
    0.40
    
    0.40
    cean
    0.40
     cornice
    0.40
    POSITIVE LOGITS
     связанные
    0.53
    哪個
    0.52
    리
    0.50
    リ
    0.48
    ام
    0.47
    م
    0.47
     связанных
    0.45
    ্লি
    0.44
    と感じ
    0.44
    ਜੀ
    0.43
    Activations Density 0.000%

    No Known Activations