© 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. 99510
    Prev
    Next
    INDEX
    Explanations

    Chain, Triangle, mean theorems

    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
    Operation
    -0.87
     kred
    -0.85
     kari
    -0.78
     komp
    -0.77
    League
    -0.77
     rings
    -0.77
     dek
    -0.75
     paja
    -0.75
    restrict
    -0.75
     văn
    -0.73
    POSITIVE LOGITS
     Fundamental
    0.95
     rules
    0.84
     rule
    0.84
     laws
    0.83
     definition
    0.82
    Fundamental
    0.79
    大小
    0.74
     Law
    0.74
     definitions
    0.71
    akuza
    0.71
    Activations Density 0.038%

    No Known Activations