© 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. 11026
    Prev
    Next
    INDEX
    Explanations

    variety of kinds

    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
     that
    -1.44
     which
    -1.30
     whose
    -1.18
     only
    -1.15
     five
    -1.09
    ⋱
    -1.02
    Ɵ
    -1.00
     лъ
    -0.98
     pregunto
    -0.96
    -
    -0.94
    POSITIVE LOGITS
    各種
    1.23
    各种
    1.17
     berbagai
    1.17
    各类
    1.17
    AfterViewInit
    1.04
     relacionados
    1.03
     notamment
    1.02
    包括
    0.98
     allerlei
    0.97
    鈊
    0.96
    Activations Density 0.040%

    No Known Activations