© 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. 259421
    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
     времени
    0.55
     эксперти
    0.55
     பயன்படுத்தி
    0.54
     теннис
    0.54
     больных
    0.54
     было
    0.50
     перспекти
    0.50
    🏏
    0.50
     армии
    0.50
     فون
    0.49
    POSITIVE LOGITS
     create
    0.50
     for
    0.48
     grad
    0.48
    ח
    0.47
    har
    0.46
    ור
    0.46
     sailboat
    0.45
    adata
    0.44
    create
    0.44
     painting
    0.44
    Activations Density 0.000%

    No Known Activations