© 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. 9499
    Prev
    Next
    INDEX
    Explanations

    qualities described by feelings or states

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

    This neuron specifically detects the idiomatic phrase “one-trick pony.”

    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
    髕
    -1.08
    `.
    -1.05
    ared
    -1.04
     Problemen
    -1.01
     ACCIDENT
    -1.01
     LIABLE
    -1.00
    heets
    -0.99
     ſeveral
    -0.97
    oughby
    -0.97
     Scritto
    -0.96
    POSITIVE LOGITS
     always
    1.83
     ALWAYS
    1.38
     usually
    1.37
     siempre
    1.12
     Usually
    1.10
     завжди
    1.10
     still
    1.07
     (
    1.07
     began
    1.07
     had
    1.06
    Activations Density 0.060%

    No Known Activations