© 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. 102377
    Prev
    Next
    INDEX
    Explanations

    noun followed by its attribute

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

    The neuron fires on single, salient noun tokens (often proper or topic-signaling words) that serve as the document’s main subject or headline term.

    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
    misen
    -1.27
    ihnachts
    -1.26
    饪
    -1.25
    rangian
    -1.23
     plentiful
    -1.18
    ForRow
    -1.16
    ٻ
    -1.16
     perdón
    -1.15
    wiſe
    -1.14
     abundant
    -1.13
    POSITIVE LOGITS
     другую
    1.17
    }
    1.15
    if
    1.14
     andere
    1.14
     notre
    1.02
     итого
    0.98
     другие
    0.96
     $#
    0.95
     weiteren
    0.94
    ító
    0.94
    Activations Density 0.580%

    No Known Activations