© 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. 7308
    Prev
    Next
    INDEX
    Explanations

    commas separating list items

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

    The neuron activates on common function words—short, high‐frequency prepositions, conjunctions, and articles.

    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
    Only
    -1.70
     cálido
    -1.65
    Before
    -1.63
    Depending
    -1.58
     encantador
    -1.57
    Even
    -1.55
    Perhaps
    -1.48
     delicada
    -1.48
    توضیحات
    -1.46
     nahezu
    -1.46
    POSITIVE LOGITS
     of
    1.99
     in
    1.54
     ovale
    1.51
     vocale
    1.49
    ではある
    1.48
     bricola
    1.45
    蹿
    1.44
     salade
    1.43
     manuel
    1.41
     latine
    1.41
    Activations Density 0.072%

    No Known Activations