© 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. 91095
    Prev
    Next
    INDEX
    Explanations

    specific compound nouns

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

    This neuron flags the content-bearing “topic” words (e.g. names, key nouns, verbs of purpose or fact) that carry the main informational load in factual or descriptive passages.

    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
     consecuencias
    -1.05
    我怎么
    -0.94
    čem
    -0.93
     comenzaron
    -0.90
    してくれた
    -0.89
     demuestra
    -0.88
     menceritakan
    -0.88
    相對
    -0.87
     extiende
    -0.87
    Lokal
    -0.86
    POSITIVE LOGITS
     missionaries
    0.87
    Thrust
    0.87
     INTERFACE
    0.83
     Thrust
    0.82
     planners
    0.81
     vistas
    0.80
     techno
    0.79
     cade
    0.79
     blend
    0.78
    hej
    0.77
    Activations Density 0.033%

    No Known Activations