© 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. 93671
    Prev
    Next
    INDEX
    Explanations

    Morning America

    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
    Populations
    -0.72
     کنیم
    -0.68
    扫描
    -0.67
     SCAN
    -0.66
    oprene
    -0.65
     full
    -0.65
    箓
    -0.63
     Много
    -0.63
    頭
    -0.62
    Farewell
    -0.61
    POSITIVE LOGITS
     Pine
    0.71
    緞
    0.67
    흐
    0.67
    cestor
    0.67
    Price
    0.66
    かと
    0.66
     новое
    0.66
     Verbreitung
    0.65
    DRAG
    0.65
    श्ले
    0.65
    Activations Density 0.058%

    No Known Activations