© 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. 39453
    Prev
    Next
    INDEX
    Explanations

    earlier times

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

    The neuron fires on the “should have + past-participle” construction (as in “should have done … first place”).

    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
     falschen
    -0.81
    umpad
    -0.81
     zufolge
    -0.77
     istor
    -0.76
    cusión
    -0.75
     aktuellen
    -0.75
     obecnie
    -0.75
     Най
    -0.75
    フラン
    -0.74
    enetrable
    -0.74
    POSITIVE LOGITS
    最初から
    2.23
     originally
    2.09
    一开始
    1.89
     initially
    1.67
     original
    1.52
    originally
    1.48
    Originally
    1.42
     earlier
    1.40
     initial
    1.37
     originalmente
    1.29
    Activations Density 0.047%

    No Known Activations