© 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. 223345
    Prev
    Next
    INDEX
    Explanations

    protection close Accident die

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

    Microsoft system operations, permissions, or attraction

    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
    োর
    0.49
     STUDIES
    0.48
     democracy
    0.46
    ﻰ
    0.46
    )
    0.44
     diagnosing
    0.43
     modesty
    0.43
     COSTS
    0.43
     interpreting
    0.42
            
    0.42
    POSITIVE LOGITS
    <unused27>
    0.52
    endente
    0.50
    pickle
    0.49
     နှစ်
    0.48
     நிலை
    0.47
     왔다
    0.47
    parat
    0.46
    ifte
    0.46
     لوبې
    0.46
    fluence
    0.46
    Activations Density 0.000%

    No Known Activations