© 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. 200706
    Prev
    Next
    INDEX
    Explanations

    "Our" or "We" after service + "Guys"

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

    turbine wheel, plug, presume

    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
     并
    0.54
     had
    0.54
     rescued
    0.49
     마
    0.48
     书
    0.48
     do
    0.47
     系统
    0.47
     成
    0.47
     K
    0.47
     sold
    0.47
    POSITIVE LOGITS
    inhas
    0.50
    fract
    0.46
    asem
    0.45
    formas
    0.45
     взаимодействия
    0.44
    の問題
    0.44
    равни
    0.43
    の高い
    0.43
    べき
    0.43
    gador
    0.43
    Activations Density 0.001%

    No Known Activations