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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78303
    Prev
    Next
    INDEX
    Explanations

    window creation string conversion

    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
     Ownership
    -0.86
     ownership
    -0.83
    زیک
    -0.78
     investigaciones
    -0.77
    改良
    -0.76
    ↺
    -0.75
    bzero
    -0.75
     palacio
    -0.74
     собственности
    -0.74
    蛹
    -0.73
    POSITIVE LOGITS
     Get
    1.09
     Set
    1.01
     Sleep
    0.96
     MessageBox
    0.91
    Get
    0.90
    Set
    0.85
    Sleep
    0.85
    wv
    0.79
     Send
    0.78
    MessageBox
    0.77
    Activations Density 0.040%

    No Known Activations