© 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. 60128
    Prev
    Next
    INDEX
    Explanations

    programming constructs and specific suffixes

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

    The neuron is selectively activating on programming source‐code tokens and syntax (e.g. keywords like package, import, class, braces, semicolons, etc.).

    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
     azonban
    -0.81
    timbangkan
    -0.76
     pulumi
    -0.76
     Kreise
    -0.73
    ndal
    -0.72
     звезд
    -0.72
    DrawerLayout
    -0.71
     уже
    -0.71
    纯
    -0.71
    𓈒
    -0.71
    POSITIVE LOGITS
    噱
    0.83
    valis
    0.77
     kanan
    0.77
     dispose
    0.77
     Abroad
    0.76
     MUNDO
    0.71
     tarik
    0.70
    eastern
    0.70
     kamu
    0.70
     changer
    0.69
    Activations Density 0.015%

    No Known Activations