© 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. 22-GEMMASCOPE-RES-131K
    7. 68407
    Prev
    Next
    INDEX
    Explanations

    concern, attention, alarm

    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
    Веду
    -1.25
    
    -1.24
    Menge
    -1.22
    Whether
    -1.20
    ↵
    -1.20
    Хороший
    -1.19
    逺
    -1.18
     レスト
    -1.17
    鯷
    -1.16
    をしました
    -1.16
    POSITIVE LOGITS
    在意
    1.30
    ,
    1.27
    皷
    1.16
    <>
    1.14
    бол
    1.12
    籥
    1.12
    𖤍
    1.09
    在乎
    1.07
    涔
    1.07
    报警
    1.05
    Activations Density 0.007%

    No Known Activations