© 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. 64021
    Prev
    Next
    INDEX
    Explanations

    discovered buried

    np_acts-logits-general · gemini-2.5-flash-lite

    step-by-step instruction phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    0.52
     Bread
    0.45
     Monitoring
    0.44
    itarian
    0.43
     மே
    0.43
     ინფორმა
    0.43
     ме
    0.43
     ז
    0.42
       
    0.42
                         
    0.42
    POSITIVE LOGITS
     Moscou
    0.54
     changement
    0.54
     commencent
    0.54
     avaient
    0.52
     Flughafen
    0.52
     došlo
    0.51
     victoire
    0.50
     degrés
    0.49
     couronne
    0.48
     pourrez
    0.48
    Activations Density 0.000%

    No Known Activations