© 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. 34-GEMMASCOPE-RES-131K
    7. 91942
    Prev
    Next
    INDEX
    Explanations

    java.util.Vector

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

    The neuron fires on occurrences of the keyword “new,” i.e. object-instantiation expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Window
    -0.94
    hã
    -0.85
    vičius
    -0.83
     window
    -0.83
    telar
    -0.82
    ższych
    -0.81
     LinearLayout
    -0.81
     gwaran
    -0.81
    ofib
    -0.80
    SequentialGroup
    -0.79
    POSITIVE LOGITS
    DayOfWeek
    0.86
     spesielt
    0.85
    Sede
    0.77
    piv
    0.77
     besonders
    0.77
    涉
    0.76
     Decide
    0.75
     Pron
    0.75
    IMPACT
    0.75
     disfru
    0.73
    Activations Density 0.008%

    No Known Activations