© 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. 10-GEMMASCOPE-RES-131K
    7. 57396
    Prev
    Next
    INDEX
    Explanations

    want to

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

    The neuron fires on occurrences of the verb “want,” i.e. explicit expressions of desire or intention.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    if
    -1.92
     like
    -1.91
    ...
    -1.80
     a
    -1.79
    like
    -1.72
     based
    -1.64
    ".
    -1.63
    ",
    -1.61
     野菜
    -1.59
    ....
    -1.55
    POSITIVE LOGITS
     andere
    1.79
    秾
    1.68
     nyeri
    1.68
    Uhr
    1.67
     всѣ
    1.66
     menek
    1.65
     jullie
    1.63
     kapak
    1.62
     merak
    1.62
     you
    1.61
    Activations Density 0.024%

    No Known Activations