© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64769
    Prev
    Next
    INDEX
    Explanations

    professionalism and dignified

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

    The neuron fires on words in testimonials that directly praise or thank someone—expressing gratitude or positive acknowledgement addressed to “you.”

    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
    :
    -1.38
    =
    -1.14
     цвят
    -1.11
    шому
    -1.06
    ᾰ
    -1.03
     bienvenue
    -1.02
    мино
    -1.01
     ratón
    -1.00
     already
    -0.99
     into
    -0.98
    POSITIVE LOGITS
    Descriere
    1.39
    makeatother
    1.28
    Preparazione
    1.26
     informée
    1.26
     during
    1.24
    ญี่ป
    1.21
    鬟
    1.18
     hábit
    1.17
    ributed
    1.16
    cipated
    1.16
    Activations Density 0.001%

    No Known Activations