© 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. 82440
    Prev
    Next
    INDEX
    Explanations

    things to 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
    しないと
    -0.84
    MacBook
    -0.83
    ון
    -0.83
    ෑ
    -0.82
    瑕
    -0.81
    zę
    -0.80
    рабаты
    -0.79
    ిం
    -0.77
    שלום
    -0.77
    ميم
    -0.77
    POSITIVE LOGITS
     avoid
    6.44
    Avoid
    5.63
    avoid
    5.59
     avoided
    5.56
     Avoid
    5.44
     avoids
    5.03
     avoidance
    4.84
     avoiding
    4.72
    避免
    4.38
     evitar
    4.28
    Activations Density 0.130%

    No Known Activations