© 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. 25948
    Prev
    Next
    INDEX
    Explanations

    sports team match events

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

    The neuron strongly activates on capitalized words and phrases—i.e. proper names and other named entities.

    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
     учре
    -0.93
     létre
    -0.84
    ischen
    -0.78
    Pase
    -0.77
    őbb
    -0.76
     mengucap
    -0.76
     bliver
    -0.75
     tertawa
    -0.75
    orar
    -0.75
     RELATIONS
    -0.75
    POSITIVE LOGITS
     travel
    2.06
     host
    1.96
     hosting
    1.90
     hosts
    1.88
     face
    1.82
     visit
    1.76
     travels
    1.74
     faces
    1.63
     visits
    1.57
     plays
    1.55
    Activations Density 0.041%

    No Known Activations