© 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. 111006
    Prev
    Next
    INDEX
    Explanations

    input and UI elements

    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
    Cyan
    -0.75
    cyan
    -0.68
    jane
    -0.67
    teva
    -0.67
    Fro
    -0.66
    peli
    -0.66
    donald
    -0.65
    hosa
    -0.65
    sna
    -0.65
     correlation
    -0.64
    POSITIVE LOGITS
     KeyCode
    1.02
     axis
    0.94
    MouseButton
    0.92
    axis
    0.88
     Axis
    0.84
    WEAK
    0.83
    KeyCode
    0.81
    Axis
    0.81
    也好
    0.79
    按下
    0.79
    Activations Density 0.004%

    No Known Activations