© 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. 10-GEMMASCOPE-RES-131K
    7. 19077
    Prev
    Next
    INDEX
    Explanations

    M followed by punctuation or numbers

    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_10/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
    ↵
    -1.23
        
    -1.22
     нарушения
    -1.15
     Pair
    -1.15
     trastorno
    -1.13
     vergleichen
    -1.13
    ac
    -1.10
    يكية
    -1.09
     No
    -1.09
     -
    -1.09
    POSITIVE LOGITS
     INCORPOR
    1.38
     LinkedList
    1.22
     VOUS
    1.21
     SIST
    1.20
    Veuillez
    1.20
     INTRODU
    1.20
     NATIONS
    1.20
     candidatura
    1.17
    他們的
    1.16
    狁
    1.15
    Activations Density 0.030%

    No Known Activations