© 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. 34813
    Prev
    Next
    INDEX
    Explanations

    import statements

    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
     Vitamina
    -0.92
     poils
    -0.84
     actionPerformed
    -0.82
    铱
    -0.81
     etapa
    -0.81
    Ꮞ
    -0.81
    Ų
    -0.80
    amico
    -0.79
    Hör
    -0.79
     tầng
    -0.78
    POSITIVE LOGITS
    scoped
    0.96
    J
    0.83
     contrast
    0.78
    vi
    0.76
    provider
    0.76
    兆
    0.75
    A
    0.75
     getenv
    0.75
    ube
    0.75
    te
    0.75
    Activations Density 0.005%

    No Known Activations