© 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. 48063
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
     totalt
    -0.92
    악
    -0.88
     in
    -0.88
    giarism
    -0.85
     Игорь
    -0.85
    девушка
    -0.84
    boldmath
    -0.83
     поскольку
    -0.82
    DeclareMath
    -0.80
     информация
    -0.79
    POSITIVE LOGITS
     consequence
    1.17
     extern
    0.89
    istered
    0.88
     default
    0.88
    artments
    0.84
     conse
    0.83
     refriger
    0.83
     artisans
    0.83
     EXPERIENCE
    0.82
    IRQn
    0.82
    Activations Density 0.028%

    No Known Activations