© 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. 10-GEMMASCOPE-RES-131K
    4. 1827
    Prev
    Next
    INDEX
    Explanations

    multiple languages and 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_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
    .
    -1.65
    蔔
    -1.55
    ائف
    -1.54
     one
    -1.53
     varying
    -1.51
     medica
    -1.46
     “¿
    -1.45
    ↵
    -1.45
    Pengertian
    -1.44
    While
    -1.43
    POSITIVE LOGITS
     he
    1.52
     outras
    1.48
     was
    1.42
    泣き
    1.34
     мужская
    1.33
     piensan
    1.32
     другими
    1.31
     женская
    1.27
     kellett
    1.27
    に行った
    1.26
    Activations Density 0.007%

    No Known Activations