© 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. 130653
    Prev
    Next
    INDEX
    Explanations

    expressing a desire or intention

    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
    葙
    -2.92
    摃
    -2.48
     để
    -2.48
    觧
    -2.41
    푣
    -2.34
    寕
    -2.33
    ㈮
    -2.27
     cittadino
    -2.22
    ⍽
    -2.22
    咴
    -2.19
    POSITIVE LOGITS
     to
    3.42
    ↵↵
    2.55
     he
    2.44
    และ
    2.17
     или
    2.11
    漼
    2.11
    および
    2.08
    椟
    2.06
    тою
    2.06
    奄
    2.03
    Activations Density 0.067%

    No Known Activations