© 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. 22-GEMMASCOPE-RES-131K
    7. 28627
    Prev
    Next
    INDEX
    Explanations

    specific items or points

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

    This neuron detects phrases that introduce enumerated list items or conditions—typically clauses immediately followed by a colon.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    這些
    -1.12
     những
    -1.07
     these
    -1.02
    这些
    -0.98
    这两
    -0.94
    ἃ
    -0.90
     those
    -0.89
    ossed
    -0.88
     some
    -0.87
    ⌕
    -0.84
    POSITIVE LOGITS
     iaitu
    0.95
     един
    0.90
    waarde
    0.86
     واحدة
    0.86
    唯一的
    0.85
    唯一
    0.85
     kuris
    0.81
    sole
    0.81
     رأس
    0.81
    Geografie
    0.79
    Activations Density 0.096%

    No Known Activations