© 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. 34-GEMMASCOPE-RES-131K
    7. 63708
    Prev
    Next
    INDEX
    Explanations

    you want or can

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

    The neuron strongly activates on occurrences of the second‐person pronoun “you,” especially in advice/instruction contexts.

    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
    probably
    -1.48
    ՚
    -1.34
    Might
    -1.32
    might
    -1.31
     Efek
    -1.28
    paravant
    -1.27
     Mungkin
    -1.27
    €”
    -1.27
     acheteurs
    -1.26
     bluz
    -1.21
    POSITIVE LOGITS
     want
    2.69
     don
    2.25
     find
    2.08
     can
    1.93
     get
    1.87
     really
    1.77
     decide
    1.73
     wanted
    1.71
     do
    1.70
     like
    1.65
    Activations Density 0.040%

    No Known Activations