© 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. 115736
    Prev
    Next
    INDEX
    Explanations

    dates and addresses

    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
     engine
    -0.79
     الاجتماعي
    -0.79
     RPM
    -0.77
    Chapter
    -0.75
     Reprodu
    -0.73
    Rocky
    -0.73
     rpm
    -0.73
     Lepid
    -0.72
    ้อมูล
    -0.71
     Wohnung
    -0.71
    POSITIVE LOGITS
     donnés
    0.86
    Faults
    0.83
    >",
    0.82
     ân
    0.81
    ders
    0.81
    tieg
    0.79
     kalend
    0.77
    乌
    0.77
     enfermos
    0.77
     aktu
    0.77
    Activations Density 0.016%

    No Known Activations