© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129489
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens that begin with a capital letter (e.g., parts of proper names or acronyms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Schottky, Sentosa, Ready, Paris, 6, Ft, Total, Real, up, Rank

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     their
    -1.16
     querían
    -1.15
     если
    -1.09
    võ
    -1.05
    instein
    -1.00
     aktuelle
    -1.00
    хотво
    -0.99
     acudi
    -0.98
    شفى
    -0.98
     kulinar
    -0.96
    POSITIVE LOGITS
     is
    1.30
     tersebut
    1.24
     was
    1.09
    This
    1.02
    😿
    1.02
     positifs
    0.97
     means
    0.96
    টি
    0.96
    HOW
    0.96
    FontAwesomeIcon
    0.96
    Activations Density 0.112%

    No Known Activations