© 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. 10-GEMMASCOPE-RES-131K
    4. 85258
    Prev
    Next
    INDEX
    Explanations

    describing consequences and explanations

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

    The neuron strongly activates on abstract nominalizations (nouns like “effect,” “observation,” “reaction,” “result,” “event,” etc.) that name events or outcomes.

    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
    ukunfts
    -1.55
     anledning
    -1.46
    各种
    -1.44
     \%}$
    -1.43
    只是
    -1.43
    ")))
    -1.38
    Interestingly
    -1.37
    Мария
    -1.36
    悒
    -1.33
    sätzlich
    -1.30
    POSITIVE LOGITS
     that
    2.39
     then
    1.95
     I
    1.87
     than
    1.76
     you
    1.57
    艄
    1.51
    色が
    1.51
    {
    1.48
     deportivo
    1.44
     następnie
    1.44
    Activations Density 0.040%

    No Known Activations