© 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. 10-GEMMASCOPE-RES-131K
    7. 75592
    Prev
    Next
    INDEX
    Explanations

    land use, planning, area, titles

    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_10/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
    咘
    -2.23
    𞤢
    -2.22
    鲧
    -2.06
    璆
    -1.96
     kompeti
    -1.96
     familien
    -1.96
    vertible
    -1.91
    
    -1.90
    
    -1.87
    vantaged
    -1.84
    POSITIVE LOGITS
     signifies
    2.25
     But
    2.25
    -
    2.19
     celebrates
    2.09
    "
    2.09
     say
    2.00
    )-
    1.98
     tells
    1.95
     theses
    1.92
     insists
    1.91
    Activations Density 0.019%

    No Known Activations