© 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. 11591
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    The neuron is highly sensitive to capitalized tokens, especially 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_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
     its
    -1.82
    ᨈ
    -1.77
     jego
    -1.69
     его
    -1.65
     októ
    -1.63
     siano
    -1.63
    它的
    -1.59
    他
    -1.58
     rempli
    -1.57
    ܊
    -1.54
    POSITIVE LOGITS
     and
    2.89
     in
    2.11
     or
    2.06
     to
    1.96
    ',
    1.77
    ",
    1.74
     at
    1.69
    '=>
    1.60
     also
    1.59
     by
    1.55
    Activations Density 0.603%

    No Known Activations