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. 8152
    Prev
    Next
    INDEX
    Explanations

    include virtual

    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
    TokenNameL
    -0.77
    {\"
    -0.77
     Constants
    -0.75
    bé
    -0.75
    Toma
    -0.74
    ゙
    -0.73
    нару
    -0.72
     вчера
    -0.71
    civ
    -0.71
     spades
    -0.71
    POSITIVE LOGITS
    mended
    0.89
     FirebaseAuth
    0.84
    月刊
    0.83
    若干
    0.79
     Institu
    0.76
    giày
    0.75
     وان
    0.73
     actionTypes
    0.73
     inclus
    0.73
     Aeronau
    0.73
    Activations Density 0.004%

    No Known Activations