© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14453
    Prev
    Next
    INDEX
    Explanations

    I wish

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

    The neuron detects occurrences of the verb “wish” (and its forms) expressing personal desire.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Breite
    -1.18
     \#:
    -1.13
     весьма
    -1.13
    lepší
    -1.13
    备案
    -1.11
     $=$
    -1.07
    eamiento
    -1.06
    ၜ
    -1.04
     engraçadas
    -1.04
    Diese
    -1.04
    POSITIVE LOGITS
     more
    1.55
    [
    1.27
     invece
    1.26
    more
    1.16
     больше
    1.14
    os
    1.13
    3
    1.13
    更多的
    1.10
     instead
    1.06
    能够
    1.06
    Activations Density 0.011%

    No Known Activations