© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13065
    Prev
    Next
    INDEX
    Explanations

    named entities and concepts

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

    The neuron strongly activates on isolated capitalized tokens that are names—e.g. brands, titles, organizations, or other proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Piscina
    -1.94
    5
    -1.92
    6
    -1.91
    8
    -1.83
     natale
    -1.83
     epoca
    -1.80
     blanda
    -1.73
     vernac
    -1.71
     Siria
    -1.70
    7
    -1.70
    POSITIVE LOGITS
    づけ
    1.87
     For
    1.85
     That
    1.85
    PasswordEncoder
    1.84
     In
    1.84
     a
    1.81
     its
    1.79
     The
    1.77
    Xna
    1.70
      
    1.63
    Activations Density 0.128%

    No Known Activations