© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115472
    Prev
    Next
    INDEX
    Explanations

    No #ifndef directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vapor
    -0.85
    TRIBUT
    -0.84
    šanās
    -0.83
     linkovi
    -0.81
    URAN
    -0.80
    harmed
    -0.80
    timely
    -0.80
    moder
    -0.77
    *{-
    -0.76
    śmie
    -0.75
    POSITIVE LOGITS
     HUD
    0.90
    PU
    0.88
    ുക
    0.88
    HUD
    0.87
     DLC
    0.84
    UI
    0.83
    ars
    0.81
    Ŗ
    0.81
    AIDS
    0.81
    Boston
    0.79
    Activations Density 0.001%

    No Known Activations