© 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. 55888
    Prev
    Next
    INDEX
    Explanations

    reading files and data

    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
    Encode
    -1.17
     export
    -1.16
    fflush
    -1.08
    encode
    -1.06
    WRITE
    -1.02
    Write
    -1.02
     write
    -0.98
     Serialize
    -0.95
    export
    -0.95
    Export
    -0.94
    POSITIVE LOGITS
     reading
    1.30
     read
    1.26
     reads
    1.20
     decoding
    1.10
    Reading
    1.09
     Reading
    1.09
     decrypt
    1.09
    读
    1.00
     đọc
    1.00
    DataInputStream
    0.96
    Activations Density 0.005%

    No Known Activations