© 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. 47885
    Prev
    Next
    INDEX
    Explanations

    want to or like to

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

    The neuron strongly detects expressions of desire, especially the word “want.”

    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
    樒
    -1.19
     ayudas
    -1.16
     purported
    -1.16
    ㈲
    -1.16
    Estar
    -1.11
     alza
    -1.11
    ;
    -1.10
    侂
    -1.09
     requisite
    -1.08
     knew
    -1.07
    POSITIVE LOGITS
     to
    2.64
     us
    1.26
     for
    1.13
     in
    1.10
     from
    1.09
     people
    1.08
    🤙
    1.07
    🎄
    1.04
    🎉
    0.97
    🤠
    0.97
    Activations Density 0.045%

    No Known Activations