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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11672
    Prev
    Next
    INDEX
    Explanations

    system state or level

    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_22/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
     dihasilkan
    -0.96
     déclarations
    -0.94
     jonka
    -0.92
    diğinde
    -0.90
    şek
    -0.89
    ittaa
    -0.89
     voidaan
    -0.89
     créations
    -0.88
     atracción
    -0.87
    もあった
    -0.87
    POSITIVE LOGITS
    isEmail
    1.03
    te
    0.99
    ┏
    0.98
    ne
    0.96
    Lmao
    0.95
     to
    0.93
    кові
    0.88
    ke
    0.88
    ki
    0.88
    zem
    0.87
    Activations Density 0.004%

    No Known Activations