Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8265
    Prev
    Next
    INDEX
    Explanations

    launchpad, springboard, linchpin

    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
    龔
    -0.75
    gatt
    -0.73
     positives
    -0.72
     Entry
    -0.69
     danger
    -0.68
    xer
    -0.68
    ニーズ
    -0.68
     напо
    -0.68
    mety
    -0.68
    נג
    -0.67
    POSITIVE LOGITS
    pin
    1.98
    pins
    1.52
    board
    1.38
    Pin
    1.37
     pin
    1.30
    head
    1.28
    PIN
    1.28
    pad
    1.18
     pins
    1.13
    boards
    1.09
    Activations Density 0.049%

    No Known Activations