© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102568
    Prev
    Next
    INDEX
    Explanations

    entrepreneurialism, fertility

    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
     unusually
    -2.92
     Surprisingly
    -2.86
    section
    -2.70
     Contrary
    -2.69
     burgeoning
    -2.64
     inherently
    -2.64
    Donativos
    -2.61
     unparalleled
    -2.58
     extravagant
    -2.56
     unrelenting
    -2.56
    POSITIVE LOGITS
    ︲
    2.66
     superfí
    2.58
    🫅
    2.48
     thre
    2.45
     vistos
    2.34
    峮
    2.34
    睃
    2.31
    
    2.30
    糨
    2.30
    呖
    2.30
    Activations Density 0.003%

    No Known Activations