© 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. 22-GEMMASCOPE-RES-131K
    7. 53978
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_22/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
    悻
    -0.88
    على
    -0.87
    royd
    -0.85
    腼
    -0.84
    othek
    -0.83
    دارد
    -0.81
     Capítulo
    -0.81
    thenReturn
    -0.81
     JOSÉ
    -0.81
    bitan
    -0.81
    POSITIVE LOGITS
     their
    1.05
     was
    1.02
    으며
    0.87
     seemed
    0.85
    унд
    0.84
     Retriever
    0.83
    的事
    0.82
     силь
    0.81
    isuus
    0.79
     尚
    0.78
    Activations Density 0.003%

    No Known Activations