© 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. 38016
    Prev
    Next
    INDEX
    Explanations

    representation theory

    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
    ={({
    -0.79
    ㄐ
    -0.79
     Wide
    -0.74
    🇷
    -0.74
     قهوه
    -0.73
    ;->
    -0.71
    ]();
    -0.71
     ethanol
    -0.71
     коль
    -0.71
    systemctl
    -0.70
    POSITIVE LOGITS
     representation
    1.35
     representations
    1.18
    representation
    1.10
    Representation
    1.09
    Represent
    1.06
     irreducible
    1.03
    representations
    1.02
     Representations
    1.00
     représent
    0.95
     Mackey
    0.94
    Activations Density 0.066%

    No Known Activations