© 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. 34-GEMMASCOPE-RES-131K
    7. 92217
    Prev
    Next
    INDEX
    Explanations

    returning or coming back

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

    The neuron detects mentions of returning or “back” contexts.

    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
    frontend
    -0.88
    ㅟ
    -0.85
    varing
    -0.85
    JAXB
    -0.85
     frontend
    -0.85
    mella
    -0.82
    ዚ
    -0.81
    つけた
    -0.73
     Frontend
    -0.73
    когда
    -0.72
    POSITIVE LOGITS
     back
    9.50
    Back
    5.28
    back
    5.13
     обратно
    4.56
     zurück
    4.41
     Back
    4.31
     BACK
    4.28
    BACK
    4.13
     terug
    4.06
     tillbaka
    3.95
    Activations Density 0.392%

    No Known Activations