© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14093
    Prev
    Next
    INDEX
    Explanations

    code statements

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in detecting Java (and similar) import declarations, firing strongly on the “import” keyword and the capitalized type or package names that follow it.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     would
    -1.16
    <eos>
    -1.13
     vokal
    -1.09
    thiết
    -1.08
    JAMIN
    -1.03
     estación
    -1.02
     korban
    -1.01
     could
    -1.00
    )。
    -0.99
     máquina
    -0.98
    POSITIVE LOGITS
    to
    1.10
    lie
    0.94
    if
    0.93
    be
    0.92
     zweiter
    0.91
    udge
    0.90
    ELA
    0.90
     weiterer
    0.89
     sogen
    0.89
     And
    0.88
    Activations Density 0.038%

    No Known Activations