© 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. 40098
    Prev
    Next
    INDEX
    Explanations

    colors describing visual elements

    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
    いいのか
    -1.31
      
    -1.20
    cluding
    -1.16
     sviluppo
    -1.15
    瑒
    -1.14
     to
    -1.11
    arted
    -1.07
    möglichen
    -1.06
     acidente
    -1.06
    hoodie
    -1.01
    POSITIVE LOGITS
     dekoratif
    1.38
     pieles
    1.27
    }\
    1.26
     tirantes
    1.17
     włosów
    1.16
     mobilya
    1.14
     sartén
    1.13
    lenir
    1.12
     renkli
    1.09
     hombros
    1.08
    Activations Density 0.020%

    No Known Activations