© 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. 688
    Prev
    Next
    INDEX
    Explanations

    pockets and zippers

    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
    andidaten
    -0.79
     choking
    -0.75
     участок
    -0.73
     hardships
    -0.73
     adipis
    -0.72
     flowered
    -0.72
     unregistered
    -0.71
    atars
    -0.71
     रा
    -0.71
    蜓
    -0.71
    POSITIVE LOGITS
     pockets
    1.20
     cargo
    0.96
     Pockets
    0.93
     functional
    0.87
    cargo
    0.84
     slash
    0.83
     Cargo
    0.82
     poc
    0.77
    Cargo
    0.75
    Slash
    0.75
    Activations Density 0.012%

    No Known Activations