© 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. 10-GEMMASCOPE-RES-131K
    7. 130883
    Prev
    Next
    INDEX
    Explanations

    code annotations and imports

    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_10/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
    薅
    -1.53
     aplique
    -1.52
    ܆
    -1.52
    ܇
    -1.52
     judicia
    -1.44
    茳
    -1.38
    ꜆
    -1.38
    BeNil
    -1.38
    つけて
    -1.38
    SuccessListener
    -1.38
    POSITIVE LOGITS
    i
    2.05
    5
    1.45
    当时
    1.41
    ‘
    1.36
    这样的
    1.34
     гораздо
    1.32
     
    1.30
     намного
    1.30
    明显
    1.30
     deschis
    1.29
    Activations Density 0.008%

    No Known Activations