© 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. 50417
    Prev
    Next
    INDEX
    Explanations

    networking protocols and libraries

    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
     deputado
    -0.93
    venant
    -0.92
     domicili
    -0.85
     loue
    -0.81
     bombilla
    -0.80
    ‌پدی
    -0.79
    inite
    -0.78
     palme
    -0.77
     granit
    -0.77
     signaler
    -0.76
    POSITIVE LOGITS
     conducir
    0.91
     дешевле
    0.77
     осо
    0.74
    鞑
    0.73
    Dela
    0.72
     трудно
    0.71
     schaut
    0.71
     estoy
    0.70
     schauen
    0.70
    immel
    0.70
    Activations Density 0.013%

    No Known Activations