© 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. 10-GEMMASCOPE-RES-131K
    4. 9142
    Prev
    Next
    INDEX
    Explanations

    of [number]

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

    The neuron never activates on any of the shown text—it does not reliably detect any pattern.

    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
     which
    -1.94
     is
    -1.75
     whose
    -1.68
    teady
    -1.65
    们的
    -1.61
     last
    -1.59
     considère
    -1.56
    ᎒
    -1.53
     ones
    -1.53
    隐隐
    -1.52
    POSITIVE LOGITS
     étrange
    1.86
     +
    1.85
     impré
    1.77
    点此
    1.75
     =
    1.71
    潆
    1.63
    ஂ
    1.62
    </sup>
    1.62
    Достоинства
    1.60
     of
    1.59
    Activations Density 0.002%

    No Known Activations