© 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. 73334
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     intptr
    -1.08
    +"/
    -1.05
    assertIs
    -0.96
     PhpStorm
    -0.92
     molding
    -0.88
    olphins
    -0.84
    Melhor
    -0.84
    sizing
    -0.84
     ويكيپيديا
    -0.83
    遗产
    -0.82
    POSITIVE LOGITS
     fractured
    0.79
     true
    0.76
    asket
    0.75
     disparate
    0.74
    そうに
    0.72
     True
    0.72
    emony
    0.71
     darkest
    0.71
    chiha
    0.71
     reconocidos
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.