© 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. 10-GEMMASCOPE-RES-131K
    7. 41931
    Prev
    Next
    INDEX
    Explanations

    expose API or interface

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

    The neuron fires on occurrences of the verb “expose” (and its morphological variants such as “exposes” or “Exposed”) in comments or documentation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     bestemt
    -1.52
    1
    -1.44
    Ꮷ
    -1.44
    ⚢
    -1.43
    橚
    -1.42
    祧
    -1.40
     innovación
    -1.39
     preferencia
    -1.39
    actéristi
    -1.38
     eradic
    -1.37
    POSITIVE LOGITS
    self
    1.80
     These
    1.66
    š
    1.63
     Without
    1.56
     for
    1.56
    sities
    1.49
     at
    1.47
     an
    1.45
     more
    1.44
     not
    1.43
    Activations Density 0.043%

    No Known Activations