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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 534
    Prev
    Next
    INDEX
    Explanations

    contrary to

    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
                
    -2.03
    ᚔ
    -1.90
     up
    -1.88
     Notably
    -1.86
    杳
    -1.84
     o
    -1.81
     Lately
    -1.79
     of
    -1.77
     into
    -1.77
     Either
    -1.75
    POSITIVE LOGITS
    袮
    2.02
     akumulator
    1.91
     säker
    1.85
     pérd
    1.81
    
    1.80
     utilizadas
    1.79
     použití
    1.75
     utilizz
    1.75
    是怎么回事
    1.73
     obligación
    1.71
    Activations Density 0.005%

    No Known Activations