© 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. 76839
    Prev
    Next
    INDEX
    Explanations

    containers, disposal, materials, products

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

    neural networks, institutional theory, nuclear research, Hispanic cultures

    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
    ።
    0.46
    paragus
    0.41
     origen
    0.41
    enged
    0.40
    ↵
    0.40
    pointe
    0.40
    scribed
    0.39
     Chama
    0.39
    panion
    0.38
    .
    0.38
    POSITIVE LOGITS
     superconductors
    0.57
    า
    0.51
    র
    0.50
    ോഷ്യ
    0.49
    岛
    0.48
    oğlu
    0.46
     outperforms
    0.46
     പോലെ
    0.46
    钅
    0.45
    듀
    0.45
    Activations Density 0.000%

    No Known Activations