© 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. 22-GEMMASCOPE-RES-131K
    7. 15385
    Prev
    Next
    INDEX
    Explanations

    departures and farewells

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

    The neuron is principally detecting verb tokens (including auxiliaries and participles) in the text.

    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
    뭄
    -0.87
    Введение
    -0.83
    icach
    -0.78
     resend
    -0.77
    んだよね
    -0.77
    Bring
    -0.77
     تجربه
    -0.76
    抡
    -0.76
     観光
    -0.76
     bluse
    -0.76
    POSITIVE LOGITS
     leave
    1.67
     leaving
    1.48
     farewell
    1.42
     departing
    1.40
     goodbye
    1.36
     parting
    1.36
     Leave
    1.20
     go
    1.20
    leave
    1.09
     leaves
    1.01
    Activations Density 0.007%

    No Known Activations