© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68083
    Prev
    Next
    INDEX
    Explanations

    quoted someone

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

    The neuron activates on the reporting verb “told” marking attributions.

    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
     that
    -1.96
    いかがでしたか
    -1.66
     следующих
    -1.61
     liknande
    -1.61
     whatnot
    -1.50
     местных
    -1.44
    '
    -1.39
    熠
    -1.38
    您好
    -1.37
    *
    -1.36
    POSITIVE LOGITS
     the
    2.14
     their
    2.13
     a
    1.89
     conferma
    1.67
     qualsiasi
    1.66
     Their
    1.64
     cualquier
    1.63
     them
    1.61
     spazi
    1.60
    鹀
    1.59
    Activations Density 0.005%

    No Known Activations