© 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. 34-GEMMASCOPE-RES-131K
    7. 25600
    Prev
    Next
    INDEX
    Explanations

    file name or path

    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_34/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
    ofstream
    -1.11
    ADA
    -0.87
    êne
    -0.83
    lden
    -0.82
     Ihres
    -0.82
    ᱩ
    -0.82
    шеб
    -0.81
    fwrite
    -0.81
     Automatically
    -0.81
    写作
    -0.80
    POSITIVE LOGITS
     reading
    0.98
    FileInputStream
    0.86
    BufferedReader
    0.84
     read
    0.84
    FileReader
    0.82
     чита
    0.82
     lesen
    0.81
    ifstream
    0.80
     attempts
    0.79
     readable
    0.76
    Activations Density 0.022%

    No Known Activations