© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38494
    Prev
    Next
    INDEX
    Explanations

    exceeding expectations or going the extra mile

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

    The neuron detects hyperbolic marketing language about going above and beyond (e.g. “going the extra mile,” “exceeding expectations,” “beyond”).

    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
     pronti
    -1.17
    FormUrlEncoded
    -1.16
     afrontar
    -1.16
    摻
    -1.06
     Violon
    -1.05
     seguimos
    -1.05
     usarlo
    -1.05
     keuze
    -1.05
    推荐阅读
    -1.05
     unirse
    -1.04
    POSITIVE LOGITS
     to
    1.78
     sogar
    1.35
     even
    1.34
     даже
    1.33
     jopa
    1.27
    s
    1.23
     customer
    1.22
     when
    1.21
     dalam
    1.13
     jika
    1.13
    Activations Density 0.002%

    No Known Activations