© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8519
    Prev
    Next
    INDEX
    Explanations

    badness, evil, or poor quality

    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
     皇族
    -2.55
    後記
    -2.08
    璈
    -2.05
    以上です
    -1.98
    賔
    -1.98
    ＝＝＝＝
    -1.93
    実際の
    -1.92
    廰
    -1.92
    谖
    -1.90
    これからの
    -1.89
    POSITIVE LOGITS
    ↵
    2.45
    或
    2.28
    what
    1.97
    或者
    1.95
     или
    1.91
     ź
    1.84
    หรือ
    1.84
     With
    1.77
    ish
    1.73
     This
    1.68
    Activations Density 0.013%

    No Known Activations