© 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. 235099
    Prev
    Next
    INDEX
    Explanations

    paint primer, These blueprints

    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
     ALL
    0.51
    同期
    0.46
    t
    0.46
    arq
    0.45
     Management
    0.45
     Architects
    0.45
     stresses
    0.43
    ت
    0.43
     Concerning
    0.42
    那個
    0.41
    POSITIVE LOGITS
     розо
    0.61
    镶
    0.53
    looped
    0.49
     শব্দটি
    0.49
     ಬಳಸ
    0.48
     개선
    0.48
     rotacao
    0.48
     dispositivi
    0.48
    鑲
    0.47
    Sliced
    0.47
    Activations Density 0.001%

    No Known Activations