© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59892
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     elettron
    -0.84
     giuri
    -0.82
     Emer
    -0.82
     empezaron
    -0.81
    ⸀
    -0.77
    urige
    -0.77
     kelapa
    -0.77
    yra
    -0.76
    рем
    -0.76
    щей
    -0.76
    POSITIVE LOGITS
    equals
    0.94
    PAID
    0.85
     uygulama
    0.81
    forderungen
    0.79
     parents
    0.73
    Internation
    0.73
    ברו
    0.72
     العملية
    0.72
    ché
    0.72
    ʁ
    0.70
    Activations Density 0.011%

    No Known Activations