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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33074
    Prev
    Next
    INDEX
    Explanations

    Unity code snippets

    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
    sterious
    -0.81
     Fassung
    -0.75
     Toen
    -0.70
    ーブル
    -0.69
    不得
    -0.68
     laterale
    -0.68
    ⓞ
    -0.68
    transform
    -0.68
     cinéma
    -0.66
     Bette
    -0.66
    POSITIVE LOGITS
    :@"
    0.82
    tilization
    0.81
    ();
    0.81
     cavity
    0.80
    minHeight
    0.79
    ASONS
    0.77
    lizes
    0.77
     ();
    0.77
    fø
    0.76
    GameManager
    0.76
    Activations Density 0.003%

    No Known Activations