© 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. 98180
    Prev
    Next
    INDEX
    Explanations

    your or you

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

    The neuron is primarily picking up on code‐specific punctuation and symbols (e.g. comment markers “//”, string delimiters, operators, dots, parentheses) rather than ordinary words.

    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
    }:\
    -0.94
     uke
    -0.93
    âche
    -0.88
     拆
    -0.88
    おきます
    -0.88
     methode
    -0.88
    Quoting
    -0.87
     complemento
    -0.85
    ństw
    -0.84
     Ռ
    -0.84
    POSITIVE LOGITS
     your
    3.06
     you
    2.34
     YOUR
    1.61
     yours
    1.45
    your
    1.41
    YOUR
    1.33
     yourself
    1.33
     YOU
    1.30
     desired
    1.26
     Your
    1.23
    Activations Density 0.075%

    No Known Activations