© 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. 84532
    Prev
    Next
    INDEX
    Explanations

    Harukawa Eizan

    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
     الشر
    -0.80
     الحدود
    -0.79
     če
    -0.78
    детский
    -0.75
    WV
    -0.75
     Če
    -0.74
    uC
    -0.74
    ctivas
    -0.74
     Samir
    -0.73
    꼼
    -0.73
    POSITIVE LOGITS
    tava
    0.77
     cosmos
    0.75
    喎
    0.72
    ourdes
    0.71
     kien
    0.70
    первых
    0.70
     Cunha
    0.70
    星星
    0.70
     waste
    0.68
    weer
    0.67
    Activations Density 0.008%

    No Known Activations