© 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. 34-GEMMASCOPE-RES-131K
    7. 48439
    Prev
    Next
    INDEX
    Explanations

    "coalition" or "transporter" or "North"

    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
     девя
    -0.75
    мені
    -0.75
     mỗi
    -0.74
     שי
    -0.73
    Население
    -0.72
     Muhammad
    -0.72
    methyl
    -0.72
    独
    -0.71
     مع
    -0.71
    meida
    -0.69
    POSITIVE LOGITS
     inked
    0.69
     berjalan
    0.67
    árez
    0.67
     atenta
    0.65
     Tec
    0.65
    GET
    0.65
    GLOBALS
    0.65
    
    0.64
    That
    0.64
     Arlene
    0.63
    Activations Density 0.763%

    No Known Activations