© 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. 103679
    Prev
    Next
    INDEX
    Explanations

    book titles and phrases

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

    The neuron strongly activates on title-case tokens—proper names and book or article titles—i.e. words that appear as part of published work titles.

    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
    cedure
    -0.87
     including
    -0.86
     solidari
    -0.86
     emporio
    -0.85
     goederen
    -0.84
    ître
    -0.83
     manipula
    -0.82
     Genus
    -0.81
     panor
    -0.80
     proverb
    -0.80
    POSITIVE LOGITS
     memoir
    1.02
    managing
    0.99
    celotti
    0.94
     cilt
    0.93
    aters
    0.92
    </em>
    0.90
    ancial
    0.90
    substantial
    0.89
     sortes
    0.88
    матика
    0.88
    Activations Density 0.073%

    No Known Activations