© 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. 19653
    Prev
    Next
    INDEX
    Explanations

    Starts of named entities or technical terms

    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
    ਗ਼
    -1.45
     mettant
    -1.43
    𝕄
    -1.41
     penser
    -1.40
     remercier
    -1.37
    をします
    -1.37
    祧
    -1.34
    cómo
    -1.30
     ktore
    -1.28
     conséquent
    -1.27
    POSITIVE LOGITS
     This
    1.37
    rrrrrrrr
    1.25
    ｙ
    1.23
     like
    1.21
     jung
    1.20
     Ima
    1.17
     all
    1.17
    ссажи
    1.16
    💗
    1.15
    ✌️
    1.14
    Activations Density 0.020%

    No Known Activations