© 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. 34-GEMMASCOPE-RES-131K
    7. 118856
    Prev
    Next
    INDEX
    Explanations

    amazon find driver

    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_34/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
     проще
    -0.85
    ہر
    -0.79
    gebirge
    -0.75
    াত
    -0.73
    لاست
    -0.73
    AddressBook
    -0.72
    졌
    -0.72
     entraîner
    -0.68
    脉
    -0.68
     artificial
    -0.67
    POSITIVE LOGITS
     вс
    0.77
    笹
    0.69
     stationed
    0.67
    kington
    0.67
    𑁍
    0.67
    ObjectModel
    0.66
     συγκ
    0.66
    Gü
    0.66
     Günter
    0.65
    мять
    0.64
    Activations Density 0.049%

    No Known Activations