© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168123
    Prev
    Next
    INDEX
    Explanations

    code definitions and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     алып
    0.39
    ằ
    0.38
     byt
    0.37
    庻
    0.37
    ॉट
    0.36
     cheerfully
    0.36
     کړئ
    0.35
     เห็น
    0.35
    yrıca
    0.35
    ஜித்
    0.35
    POSITIVE LOGITS
    문화
    0.38
    vra
    0.37
     extr
    0.36
     Elimination
    0.36
    vae
    0.36
    ֻ
    0.36
     qualcosa
    0.35
     Mitochondrial
    0.35
    væ
    0.35
    вай
    0.35
    Activations Density 0.001%

    No Known Activations