© 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. 34-GEMMASCOPE-RES-131K
    7. 82714
    Prev
    Next
    INDEX
    Explanations

    verb followed by your

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

    The neuron fires on interface‐ or setup‐related action words (imperative verbs and directional cues) that guide the user to perform tasks (e.g. refine, click, set up, update).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Their
    -1.87
    Its
    -1.79
     leurs
    -1.74
     unserer
    -1.69
     ihrer
    -1.63
     خودش
    -1.57
     meiner
    -1.57
     ihres
    -1.47
     ему
    -1.43
     нашим
    -1.40
    POSITIVE LOGITS
     your
    13.69
    your
    5.03
     Your
    4.94
    你的
    4.66
    Your
    4.44
     you
    4.38
     votre
    4.28
    您的
    4.28
     YOUR
    4.28
     vaše
    4.13
    Activations Density 0.663%

    No Known Activations