© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94184
    Prev
    Next
    INDEX
    Explanations

    needle insertion or probing

    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
    API
    -0.81
     Trello
    -0.75
     EDR
    -0.73
     sonnen
    -0.73
    heads
    -0.71
     politicians
    -0.71
    entgen
    -0.69
     origem
    -0.69
     Rolling
    -0.67
    target
    -0.66
    POSITIVE LOGITS
     ske
    1.26
     tester
    1.21
     inserted
    1.20
     clean
    1.16
     toothpick
    1.13
     test
    1.11
     Ske
    1.05
     Insert
    1.01
    inserted
    1.01
    Ske
    1.00
    Activations Density 0.009%

    No Known Activations