© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67851
    Prev
    Next
    INDEX
    Explanations

    this is

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

    The neuron is specialized to pick out the common discourse pivot “That, of course, is…” (and very similar parenthetical phrases built around a demonstrative, “of course,” commas, and the verb “is”).

    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
    whelmed
    -1.80
    bedded
    -1.66
    arching
    -1.61
    joyed
    -1.55
     its
    -1.53
    ars
    -1.48
     tärke
    -1.47
    DOES
    -1.40
     ruok
    -1.37
    鲼
    -1.37
    POSITIVE LOGITS
     would
    1.69
     should
    1.64
     is
    1.60
     όταν
    1.41
    私の
    1.36
    年は
    1.30
     my
    1.28
     ketika
    1.23
     управління
    1.19
    .
    1.19
    Activations Density 0.016%

    No Known Activations