© 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. 10-GEMMASCOPE-RES-131K
    7. 71540
    Prev
    Next
    INDEX
    Explanations

    reason for desire or need

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

    The neuron activates on expressions of personal desire—especially the verb “want” (and its variants “wants,” “want to,” etc.).

    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
     as
    -2.36
     at
    -1.94
     by
    -1.88
     in
    -1.83
     While
    -1.80
     on
    -1.73
     through
    -1.70
     Although
    -1.70
     went
    -1.69
     during
    -1.66
    POSITIVE LOGITS
     également
    1.61
     principalement
    1.59
    edere
    1.54
    mainly
    1.49
     ní
    1.47
     aplicaciones
    1.46
    primarily
    1.45
    mostly
    1.43
    archiwizowane
    1.41
    鰱
    1.41
    Activations Density 0.040%

    No Known Activations