© 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. 22-GEMMASCOPE-RES-131K
    7. 16136
    Prev
    Next
    INDEX
    Explanations

    extracting text content

    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_22/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
     包装
    -1.30
    甞
    -1.27
    呖
    -1.23
    UIControlState
    -1.21
    帏
    -1.20
    רט
    -1.19
    坼
    -1.16
    笵
    -1.16
     联
    -1.16
     手工
    -1.16
    POSITIVE LOGITS
    There
    1.52
     or
    1.52
    Surprisingly
    1.36
    Shortly
    1.29
     diligent
    1.23
    After
    1.22
     undeniably
    1.19
    ранее
    1.16
     Surprisingly
    1.15
     Mitgliedern
    1.14
    Activations Density 0.003%

    No Known Activations