© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106481
    Prev
    Next
    INDEX
    Explanations

    assembly registers and memory addresses

    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
    cetype
    -0.75
     xhr
    -0.71
    keda
    -0.70
     essere
    -0.70
     tanker
    -0.69
     堂
    -0.68
     Bericht
    -0.68
    ╼
    -0.68
    戚
    -0.67
    atsu
    -0.67
    POSITIVE LOGITS
     PC
    1.74
    PC
    1.71
     pc
    1.50
    pc
    1.48
     PCs
    1.45
    Pc
    1.36
     IP
    1.34
     Pc
    1.32
    EIP
    1.25
    IP
    1.24
    Activations Density 0.051%

    No Known Activations