© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68811
    Prev
    Next
    INDEX
    Explanations

    listing other items

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

    The neuron strongly activates on words that introduce or head lists of examples—e.g. “include,” “issues,” “members,” “may,” “causes,” etc.—so its main function is spotting list-introducing or enumeration signals.

    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
    感じです
    -1.21
     that
    -1.17
     stratégies
    -1.13
     protoimpl
    -1.10
    Gilla
    -1.08
     richied
    -1.07
    ditor
    -1.06
    thargy
    -1.02
    neiden
    -1.02
    ">(</
    -1.02
    POSITIVE LOGITS
     other
    2.45
    อื่น
    1.69
    other
    1.66
     अन्य
    1.57
     otros
    1.55
     остальных
    1.53
     другие
    1.52
     also
    1.51
     других
    1.48
     سایر
    1.45
    Activations Density 0.046%

    No Known Activations