© 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. 10343
    Prev
    Next
    INDEX
    Explanations

    Edgar Lungu, Chamber, Shrine

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

    The Parisian, 3rd, Brightlands, software

    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
     System
    0.47
     JavaScript
    0.46
     x
    0.46
     system
    0.46
     websites
    0.46
     counties
    0.46
     r
    0.45
     năm
    0.45
     bảng
    0.44
     numpy
    0.44
    POSITIVE LOGITS
    Encom
    0.57
    Conse
    0.52
    נ
    0.52
    при
    0.52
    팡
    0.52
    ט
    0.51
    politik
    0.51
    Commande
    0.51
    tempor
    0.50
    Geme
    0.50
    Activations Density 0.039%

    No Known Activations