© 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. 662
    Prev
    Next
    INDEX
    Explanations

    URLs or web links

    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
     but
    -1.69
    是一个
    -1.55
    s
    -1.50
     #"
    -1.38
     européennes
    -1.37
     vivía
    -1.37
     intensively
    -1.35
     сюжет
    -1.33
    Gén
    -1.33
    如果有
    -1.30
    POSITIVE LOGITS
     musíte
    1.87
     success
    1.67
     rezultat
    1.66
    沨
    1.65
    ходим
    1.64
    なんですね
    1.58
     wektor
    1.57
     problemu
    1.53
     사람
    1.52
    都不会
    1.51
    Activations Density 0.009%

    No Known Activations