© 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. 34-GEMMASCOPE-RES-131K
    7. 53882
    Prev
    Next
    INDEX
    Explanations

    Polish names and places

    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
     pneu
    -0.80
     מפ
    -0.79
     frans
    -0.78
     провер
    -0.76
     divertir
    -0.76
    缺点
    -0.75
    挂
    -0.75
     ră
    -0.75
    Leit
    -0.74
     pista
    -0.73
    POSITIVE LOGITS
    ądź
    0.89
    б
    0.88
     Breaking
    0.83
    本土
    0.80
    晔
    0.76
     breakage
    0.75
    打破
    0.75
     若い
    0.73
    tablir
    0.73
     tuvo
    0.73
    Activations Density 0.008%

    No Known Activations