© 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. 25685
    Prev
    Next
    INDEX
    Explanations

    focus on one thing

    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
    Kategorie
    -1.16
     âme
    -1.05
    各类
    -1.01
    +}\
    -1.00
     vůbec
    -1.00
    診察
    -0.99
    Antworten
    -0.98
    始まり
    -0.96
    Заключение
    -0.96
    Недо
    -0.95
    POSITIVE LOGITS
     focus
    1.75
    focus
    1.42
     fewer
    1.42
     only
    1.38
     focuses
    1.34
     concentrate
    1.33
     focused
    1.32
    Focus
    1.23
     tylko
    1.23
     только
    1.20
    Activations Density 0.028%

    No Known Activations