© 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. 57689
    Prev
    Next
    INDEX
    Explanations

    resignation and quitting

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

    The neuron fires on words and phrases that indicate someone stepping down, quitting, or formally resigning from a role.

    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
    로운
    -0.80
    luste
    -0.79
     zabur
    -0.79
    erobe
    -0.77
     discontinued
    -0.76
     bean
    -0.76
     returned
    -0.74
    onka
    -0.71
     expelled
    -0.71
    cobs
    -0.71
    POSITIVE LOGITS
     resignation
    2.16
     tendered
    1.70
    resign
    1.53
     resign
    1.52
     démission
    1.28
     submitted
    1.09
    辞职
    1.09
     letter
    1.09
     renuncia
    1.08
     resigning
    1.03
    Activations Density 0.025%

    No Known Activations