© 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. 41879
    Prev
    Next
    INDEX
    Explanations

    fear or aversion

    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
    轳
    -3.06
    idjan
    -2.63
     prioriti
    -2.53
    鈰
    -2.47
     tragé
    -2.44
     When
    -2.42
    縂
    -2.42
    隄
    -2.39
    捩
    -2.36
    大腿
    -2.28
    POSITIVE LOGITS
    ౭
    2.95
    謦
    2.80
    狴
    2.67
    赑
    2.66
    鱨
    2.55
    ’
    2.38
    蚡
    2.31
    蛩
    2.28
     beginnen
    2.27
    {
    2.27
    Activations Density 0.007%

    No Known Activations