© 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. 117011
    Prev
    Next
    INDEX
    Explanations

    text = or text :

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

    The neuron strongly activates on occurrences of “Text” as a code‐snippet token (e.g. the Text property in UI/control definitions).

    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
     [][]
    -0.83
     gelten
    -0.81
     pronom
    -0.80
     וכו
    -0.79
     Baru
    -0.79
    Vida
    -0.79
     rdf
    -0.79
    nados
    -0.79
    çants
    -0.78
    ↤
    -0.78
    POSITIVE LOGITS
    ”;
    0.88
    ;,
    0.84
     gdzie
    0.81
     estampado
    0.81
     почему
    0.80
    ,;
    0.80
    \|_{\
    0.77
    ே
    0.77
     fingerprint
    0.77
     options
    0.77
    Activations Density 0.003%

    No Known Activations