© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208067
    Prev
    Next
    INDEX
    Explanations

    businesses such as

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

    flow star

    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
    Negative Logits
     Beach
    0.43
    栄養
    0.42
     Hydro
    0.41
     Fatigue
    0.41
     ও
    0.41
     पोषक
    0.40
     Odysseus
    0.40
    乗り
    0.40
     Ore
    0.40
     Nathaniel
    0.40
    POSITIVE LOGITS
     meios
    0.52
    톄
    0.51
    краё
    0.50
    ёг
    0.48
    Refer
    0.48
    ੴ
    0.48
     généraux
    0.47
     між
    0.46
    뎅
    0.46
    语义
    0.45
    Activations Density 0.001%

    No Known Activations