© 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. 10-GEMMASCOPE-RES-131K
    7. 111075
    Prev
    Next
    INDEX
    Explanations

    sports teams and research terms

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

    The neuron detects sequences of uppercase letters (often mixed with digits or hyphens), i.e. technical acronyms, abbreviations, and alphanumeric codes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -1.80
     at
    -1.56
     after
    -1.37
     stycznia
    -1.35
     cuenca
    -1.34
     only
    -1.28
     października
    -1.25
     even
    -1.24
     just
    -1.23
     Comunicação
    -1.23
    POSITIVE LOGITS
     trouxe
    1.31
    非常的
    1.27
     reveló
    1.25
     conhece
    1.21
     proporciona
    1.20
     certaines
    1.17
     chiede
    1.16
     coloca
    1.16
     perceber
    1.16
     ottenere
    1.14
    Activations Density 0.970%

    No Known Activations