© 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. 102560
    Prev
    Next
    INDEX
    Explanations

    Q or After phrases

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

    The neuron fires on Android support library package names (e.g. “android.support.design.widget”), including design, widget, constraint‐layout, and related module identifiers.

    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
    ActionPerformed
    -0.84
     from
    -0.82
    EST
    -0.71
    ORDER
    -0.71
     for
    -0.70
    ͑
    -0.70
    ---
    -0.69
    énération
    -0.68
     it
    -0.68
     que
    -0.67
    POSITIVE LOGITS
     سپاه
    0.82
     Espresso
    0.82
     Betsy
    0.80
     espresso
    0.77
    ismen
    0.77
    affiche
    0.76
    ůr
    0.76
    Bruno
    0.75
     RSC
    0.75
    LOGOUT
    0.75
    Activations Density 0.003%

    No Known Activations