© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33486
    Prev
    Next
    INDEX
    Explanations

    java package names

    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
     ۱۶
    -1.13
     Iš
    -1.03
    geen
    -1.00
     ۱۱
    -0.99
    だからこそ
    -0.98
     Özel
    -0.98
    Trichloroethane
    -0.96
     njia
    -0.95
     المصرية
    -0.95
     Esses
    -0.94
    POSITIVE LOGITS
    OBJETIVOS
    1.06
    CÁ
    1.04
     causado
    0.97
    Abrir
    0.97
    »,
    0.97
    Lundi
    0.96
    饪
    0.96
     değildir
    0.96
    ünden
    0.96
     deoarece
    0.96
    Activations Density 0.026%

    No Known Activations