© 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. 91208
    Prev
    Next
    INDEX
    Explanations

    parsing or reading code

    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
    bouncycastle
    -0.84
     }-
    -0.83
    Euc
    -0.81
    gging
    -0.79
     zwarte
    -0.78
    ulators
    -0.77
    divided
    -0.76
     kereta
    -0.75
    ouchable
    -0.75
    𝕬
    -0.74
    POSITIVE LOGITS
    parse
    0.88
     reads
    0.81
     continuing
    0.78
     reading
    0.77
    Parser
    0.76
     continues
    0.73
    parser
    0.73
    ตรง
    0.72
     continue
    0.71
     read
    0.71
    Activations Density 0.000%

    No Known Activations