© 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. 87230
    Prev
    Next
    INDEX
    Explanations

    ping or Pind

    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
     acontecer
    -0.80
     singola
    -0.75
     conocemos
    -0.73
     bright
    -0.73
     会社
    -0.73
     assumed
    -0.72
    setView
    -0.71
    ptăm
    -0.71
     contrast
    -0.71
     Up
    -0.71
    POSITIVE LOGITS
     Pong
    1.34
    pong
    1.29
     pong
    1.28
    Pong
    1.16
     Ping
    1.12
    xDB
    1.05
    jmu
    1.02
    demic
    1.01
    ping
    0.93
    ding
    0.92
    Activations Density 0.007%

    No Known Activations