© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129586
    Prev
    Next
    INDEX
    Explanations

    places and names

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

    The neuron activates most strongly on multi‐syllable proper nouns or specific named entities (e.g. person names, place names, titles).

    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
     lycée
    -1.55
     straff
    -1.45
    捽
    -1.44
    ﻐ
    -1.42
     Novembre
    -1.41
     entreprise
    -1.38
    tempts
    -1.38
    尨
    -1.36
     arbre
    -1.34
     ideen
    -1.34
    POSITIVE LOGITS
    <bos>
    1.72
     that
    1.67
     This
    1.48
     nothing
    1.46
     to
    1.41
     calificación
    1.41
    非常に
    1.39
     mesmas
    1.38
     damaligen
    1.37
     very
    1.36
    Activations Density 0.112%

    No Known Activations