© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78460
    Prev
    Next
    INDEX
    Explanations

    byte/bytes related concepts

    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
    newArrayList
    -0.98
    くださいませ
    -0.98
     famosas
    -0.97
    spyOn
    -0.95
    writeString
    -0.94
    šana
    -0.89
    apatalk
    -0.89
    berapa
    -0.89
     jugend
    -0.89
     success
    -0.88
    POSITIVE LOGITS
     bytes
    1.53
     byte
    1.48
    byte
    1.43
    bytes
    1.41
    字节
    1.22
     endian
    1.13
    padded
    1.13
    Bytes
    1.10
    uint
    1.09
     Packers
    1.08
    Activations Density 0.018%

    No Known Activations