© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110797
    Prev
    Next
    INDEX
    Explanations

    waiting until something resolved

    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
     inicios
    -1.01
     시작
    -1.00
     pourtant
    -1.00
    ◔
    -1.00
     même
    -0.99
     BioLib
    -0.98
    ILAR
    -0.97
    RAEL
    -0.97
     rápidamente
    -0.96
    簷
    -0.96
    POSITIVE LOGITS
     further
    2.13
     sufficient
    1.78
     more
    1.77
     complete
    1.66
     fully
    1.64
     proper
    1.58
     adequate
    1.54
     properly
    1.54
     clearer
    1.48
     better
    1.44
    Activations Density 0.049%

    No Known Activations