© 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. 128098
    Prev
    Next
    INDEX
    Explanations

    quotation marks

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

    This neuron activates on opening quotation marks that introduce a character’s spoken dialogue.

    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
     and
    -1.86
     первых
    -1.47
     A
    -1.41
     '
    -1.38
    ’
    -1.36
    ”.
    -1.34
     возможность
    -1.34
    Z
    -1.32
     These
    -1.32
     “
    -1.29
    POSITIVE LOGITS
     bancaria
    1.56
     operativa
    1.46
     vengo
    1.44
    jścia
    1.44
     pesso
    1.42
    结语
    1.41
     marea
    1.39
    皷
    1.34
     interessa
    1.32
     autonomia
    1.31
    Activations Density 0.004%

    No Known Activations