© 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. 10-GEMMASCOPE-RES-131K
    7. 48525
    Prev
    Next
    INDEX
    Explanations

    avoid situations

    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_10/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
    yssey
    -1.34
    お楽しみに
    -1.31
    ✆
    -1.27
    stva
    -1.23
    もう少し
    -1.22
    饽
    -1.20
    楽しみにして
    -1.20
    ILITIES
    -1.19
     geschieht
    -1.19
     this
    -1.18
    POSITIVE LOGITS
     napisał
    1.48
    Avoid
    1.41
     mientras
    1.35
    高
    1.27
     Minutes
    1.19
     while
    1.17
    Expert
    1.16
    ৯
    1.16
     mentre
    1.16
     enquanto
    1.15
    Activations Density 0.037%

    No Known Activations