© 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. 91060
    Prev
    Next
    INDEX
    Explanations

    reading byte buffer

    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
     المح
    -0.77
     ją
    -0.76
     energética
    -0.76
     ranked
    -0.75
    UseCase
    -0.74
    asari
    -0.74
     bieg
    -0.74
    ônimo
    -0.73
    umbent
    -0.73
    谩
    -0.73
    POSITIVE LOGITS
    ༒
    0.84
    atia
    0.82
    iados
    0.81
     byte
    0.80
     Azevedo
    0.77
     Armageddon
    0.76
    会上
    0.75
     AVAILABLE
    0.75
     detal
    0.75
    ("~/
    0.74
    Activations Density 0.007%

    No Known Activations