© 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. 84691
    Prev
    Next
    INDEX
    Explanations

    Java IO operations

    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
     during
    -1.10
     now
    -1.05
     because
    -0.98
     some
    -0.94
     seven
    -0.92
     nine
    -0.91
    0
    -0.90
     discovered
    -0.87
     peer
    -0.86
     without
    -0.84
    POSITIVE LOGITS
    Serializable
    1.13
    ból
    1.05
    EEEE
    1.03
    IOException
    1.00
    metries
    0.98
    ,",
    0.98
     eſſ
    0.96
    println
    0.93
    BIÉN
    0.93
    ből
    0.92
    Activations Density 0.003%

    No Known Activations