© 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. 79987
    Prev
    Next
    INDEX
    Explanations

    your, our, theirs

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

    The neuron responds to descriptive, promotional language—i.e. tokens in product‐description or marketing copy.

    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
    ּוֹ
    -1.13
     большинстве
    -1.11
     различных
    -1.09
    なども
    -1.09
     choroby
    -1.08
    knapp
    -1.07
     العديد
    -1.06
     cercana
    -1.05
    われている
    -1.05
     няколко
    -1.05
    POSITIVE LOGITS
     your
    1.68
     our
    1.30
     आपके
    1.20
     ваш
    1.18
    !
    1.13
    。
    1.08
    你的
    1.07
     вашу
    1.05
    your
    1.03
     растения
    1.02
    Activations Density 0.061%

    No Known Activations