© 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. 103163
    Prev
    Next
    INDEX
    Explanations

    plus, +, +, positive confirmation

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

    The neuron activates strongly on named entities—proper nouns such as place names, organizations, event titles, or quoted 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_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
    Flashcards
    -0.93
    belongsTo
    -0.86
     restoran
    -0.84
    Kolor
    -0.84
    nande
    -0.81
     boks
    -0.79
     Ging
    -0.79
     when
    -0.79
    Çok
    -0.79
     hangi
    -0.78
    POSITIVE LOGITS
    +,
    1.20
    ”,
    1.17
    ”.
    1.16
    Plus
    1.15
    plus
    1.12
    +.
    1.10
     plus
    1.06
    ".
    1.05
     Plus
    1.04
    ",
    1.01
    Activations Density 0.016%

    No Known Activations