© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    pocket book, camera, or monsters

    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
     Comercio
    -0.77
    1
    -0.75
     pulmonar
    -0.75
     Heated
    -0.73
    去做
    -0.73
     如何
    -0.73
     недели
    -0.72
     geholfen
    -0.71
     underta
    -0.71
     原因
    -0.71
    POSITIVE LOGITS
    knife
    1.23
     pocket
    1.11
    book
    1.07
     sized
    1.06
     rocket
    1.06
     Pocket
    1.05
    Pocket
    0.99
     cadáver
    0.99
     galletas
    0.97
     warmer
    0.94
    Activations Density 0.008%

    No Known Activations