© 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. 91078
    Prev
    Next
    INDEX
    Explanations

    dura followed by matter or bility

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

    This neuron fires on occurrences of the character sequence “dura” (whether as a standalone word or part of a longer token).

    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
     metast
    -0.68
    Malo
    -0.68
     Ulysses
    -0.67
     hilar
    -0.65
    latz
    -0.64
    unjung
    -0.64
    PERT
    -0.64
    '||
    -0.64
    getElementsBy
    -0.63
     للد
    -0.63
    POSITIVE LOGITS
    atians
    0.76
    ceton
    0.73
     מצ
    0.69
    oin
    0.69
    ock
    0.69
     martes
    0.68
    ecznie
    0.66
    🌮
    0.66
    京东
    0.66
    raquo
    0.66
    Activations Density 0.071%

    No Known Activations