© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99017
    Prev
    Next
    INDEX
    Explanations

    Polish places and names

    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
    コンセプト
    -0.88
     in
    -0.85
    čnosti
    -0.85
     COMPOUNDS
    -0.82
     including
    -0.82
     gwar
    -0.82
     腿
    -0.80
     médec
    -0.79
     jantung
    -0.77
    ující
    -0.77
    POSITIVE LOGITS
     mieste
    1.31
     miest
    1.23
     miesto
    1.20
     komer
    0.95
     sebel
    0.94
    日本
    0.94
    ORUS
    0.92
    Gam
    0.90
    FOLIO
    0.90
     fotografii
    0.89
    Activations Density 0.003%

    No Known Activations