© 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. 12053
    Prev
    Next
    INDEX
    Explanations

    states within, buying songs, Brødrene Hansen

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

    The neuron fires on multi‐token proper names and titles—especially formal organization or domain names (e.g. “the Member States within the Council,” “Ordensstaat Burgund,” “.org” URLs).

    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
     sermons
    -0.96
     seleccionados
    -0.95
     wybór
    -0.83
     pls
    -0.82
     escuchar
    -0.82
     когато
    -0.81
    lowns
    -0.80
     Prenez
    -0.79
     plunder
    -0.77
     Freunden
    -0.77
    POSITIVE LOGITS
     désigner
    1.02
     keer
    1.02
     déposer
    1.00
     constater
    0.93
     reprendre
    0.93
    somewhat
    0.93
    водом
    0.91
    mostly
    0.91
     susi
    0.90
     tiek
    0.89
    Activations Density 0.010%

    No Known Activations