© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116492
    Prev
    Next
    INDEX
    Explanations

    bytes and uint8 data types

    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
    writeInt
    -0.96
     ribuan
    -0.92
     long
    -0.91
    Thousands
    -0.91
     thousands
    -0.87
    поли
    -0.85
    uſ
    -0.84
     like
    -0.82
     positifs
    -0.82
     thousand
    -0.80
    POSITIVE LOGITS
    ReadByte
    1.24
    uchar
    1.10
    BYTE
    1.06
     byte
    0.98
    Byte
    0.98
    byte
    0.94
    UCHAR
    0.90
    writeByte
    0.87
     Byte
    0.85
     ascii
    0.82
    Activations Density 0.018%

    No Known Activations