© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    code removal

    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
    ciano
    -0.93
    SafeAreaView
    -0.88
    ingual
    -0.81
    rewind
    -0.80
     πρ
    -0.80
    établir
    -0.79
     родился
    -0.79
     acondicion
    -0.79
    strncmp
    -0.79
    closes
    -0.79
    POSITIVE LOGITS
     removal
    2.13
     remove
    2.03
     removed
    1.89
     Remove
    1.79
     removing
    1.78
     removeFrom
    1.75
     removes
    1.74
     Removing
    1.67
     Removal
    1.65
    removeChild
    1.63
    Activations Density 0.004%

    No Known Activations