© 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. 83294
    Prev
    Next
    INDEX
    Explanations

    avoid

    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
     disagreement
    -0.83
    overset
    -0.82
     stubborn
    -0.81
     Geduld
    -0.81
     いる
    -0.81
    jsonPath
    -0.80
    EXPORT
    -0.79
    umably
    -0.79
    indale
    -0.79
     painless
    -0.79
    POSITIVE LOGITS
     avoid
    2.23
     avoidance
    2.14
    avoid
    2.06
    Avoid
    2.03
     avoided
    1.95
     Avoid
    1.93
     avoids
    1.91
     avoiding
    1.84
     Avoiding
    1.75
     AVOID
    1.66
    Activations Density 0.038%

    No Known Activations