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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129754
    Prev
    Next
    INDEX
    Explanations

    discussing specific topics

    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
    šiť
    -1.05
     разных
    -1.05
     millet
    -1.05
     різних
    -1.04
     Pilate
    -1.02
    tellten
    -1.01
     různých
    -1.00
     verschillende
    -0.96
     różnych
    -0.95
     Rhodesia
    -0.94
    POSITIVE LOGITS
     the
    1.18
     that
    0.94
    стояние
    0.90
    malı
    0.89
    gı
    0.84
    哆
    0.83
     maiores
    0.82
    facebook
    0.81
     Kardinal
    0.80
    className
    0.80
    Activations Density 0.043%

    No Known Activations