© 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. 73741
    Prev
    Next
    INDEX
    Explanations

    measurement and labeling

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

    documentation and significance

    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
     که
    0.55
    ﻒ
    0.54
     subterranean
    0.53
     canals
    0.52
     یه
    0.52
     ocorr
    0.48
     ニュー
    0.48
     arcane
    0.47
    ऽ
    0.46
    قطه
    0.45
    POSITIVE LOGITS
     Tabs
    0.42
     lý
    0.42
    标签
    0.40
    廪
    0.40
     tập
    0.40
     शेड्यूल
    0.39
     Encryption
    0.39
    tabs
    0.39
     Inventory
    0.39
    ख्ती
    0.39
    Activations Density 0.000%

    No Known Activations