© 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. 70078
    Prev
    Next
    INDEX
    Explanations

    listing with such

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

    The neuron is detecting and boosting content‐bearing nouns—especially domain-specific technical or key topic terms—throughout the text.

    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
     seleccionamos
    -1.52
     informó
    -1.48
     reveló
    -1.40
     confirmó
    -1.35
    OGRAPH
    -1.31
     pidió
    -1.31
     aseguró
    -1.31
    íu
    -1.30
     ofrecemos
    -1.29
     recordó
    -1.23
    POSITIVE LOGITS
     such
    11.63
    such
    7.19
     like
    6.66
     таких
    5.94
     такие
    5.88
    Such
    5.78
     SUCH
    5.13
     takich
    4.91
     zoals
    4.88
     مثل
    4.75
    Activations Density 1.811%

    No Known Activations