© 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. 84182
    Prev
    Next
    INDEX
    Explanations

    Postmenopausal, retrospective, open, Bob's, Q:

    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
    Miracle
    -0.76
     soff
    -0.75
     Miracle
    -0.74
    Donut
    -0.73
    骅
    -0.71
     mola
    -0.70
    ▨
    -0.69
    cocci
    -0.68
     sesso
    -0.68
     ساح
    -0.66
    POSITIVE LOGITS
     managerial
    1.01
     capac
    0.91
     décisions
    0.89
     Operations
    0.88
     Managerial
    0.84
     القرار
    0.80
    Operations
    0.79
     cordon
    0.79
     RFID
    0.78
     perishable
    0.78
    Activations Density 0.015%

    No Known Activations