© 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. 87241
    Prev
    Next
    INDEX
    Explanations

    channel, channeling, channeled

    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
    慙
    -1.62
     wachsen
    -1.54
    3
    -1.50
     необходимости
    -1.48
    ⑧
    -1.45
    
    -1.45
    游戏的
    -1.44
    structors
    -1.41
     glaring
    -1.39
    れました
    -1.38
    POSITIVE LOGITS
     into
    1.87
    ;
    1.79
    )
    1.66
     to
    1.63
    蟥
    1.54
    cienza
    1.53
    ENCIL
    1.53
    ctic
    1.47
    ,”
    1.46
     Não
    1.46
    Activations Density 0.068%

    No Known Activations