Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 125
    Prev
    Next
    INDEX
    Explanations

    Swift programming language constructs

    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
    ßlich
    -0.79
     extinct
    -0.79
     unintentionally
    -0.79
     ασ
    -0.77
    ExtendWith
    -0.74
     maris
    -0.70
     Dictionnaire
    -0.70
     ἀ
    -0.70
     blindly
    -0.69
     synonymous
    -0.69
    POSITIVE LOGITS
    リエ
    0.84
    argent
    0.76
     zelf
    0.74
    urge
    0.73
    ходы
    0.72
    fds
    0.71
    mple
    0.70
    ximation
    0.69
     Pencil
    0.69
     imágenes
    0.69
    Activations Density 0.087%

    No Known Activations