© 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. 67933
    Prev
    Next
    INDEX
    Explanations

    multilingual abbreviations and codes

    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
     perdidos
    -0.78
     Bieber
    -0.78
     Polskiej
    -0.76
    除此
    -0.75
    与此
    -0.75
    livion
    -0.73
     веществ
    -0.73
     justamente
    -0.72
     aislados
    -0.72
    Without
    -0.72
    POSITIVE LOGITS
    ům
    0.98
     alvo
    0.87
    そして
    0.85
    riffen
    0.84
    stadt
    0.82
    Healing
    0.82
     病院
    0.82
    क्षित
    0.82
    tiskt
    0.79
    ַע
    0.79
    Activations Density 0.093%

    No Known Activations