© 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. 10-GEMMASCOPE-RES-131K
    7. 40582
    Prev
    Next
    INDEX
    Explanations

    anthology and compilation of works

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

    The neuron strongly activates on the word “anthology” (and related forms indicating a collected volume or compilation).

    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
    埽
    -2.36
    b
    -2.28
    these
    -2.11
    our
    -1.90
    O
    -1.77
     we
    -1.73
     atau
    -1.69
    we
    -1.67
    ieważ
    -1.64
     It
    -1.63
    POSITIVE LOGITS
     of
    2.41
    ANDED
    1.95
    .”
    1.89
    ᚔ
    1.86
    ༛
    1.72
    :“
    1.71
    秝
    1.70
    牆
    1.69
     „
    1.65
     })
    1.65
    Activations Density 0.009%

    No Known Activations