© 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. 54289
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures

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

    The neuron fires on occurrences of class or generic type names—especially when used in constructor calls or type instantiations.

    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
    morphosis
    -0.91
     знать
    -0.88
     conoce
    -0.83
     gitara
    -0.81
     específicos
    -0.81
     FetchType
    -0.81
     februarie
    -0.78
     know
    -0.77
    iration
    -0.76
     imaging
    -0.76
    POSITIVE LOGITS
    <
    2.48
    </
    1.16
    <tbody>
    0.92
     <
    0.90
     vieill
    0.85
    .<
    0.83
    \<
    0.82
    <sup>
    0.82
    ський
    0.81
    <table>
    0.81
    Activations Density 0.032%

    No Known Activations