© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 57550
    Prev
    Next
    INDEX
    Explanations

    return and homecoming events

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

    The neuron detects words and phrases related to returning or “coming back” (e.g., homecoming, regroup, returns, awakening).

    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
    </i>
    -3.08
     -
    -2.94
     When
    -2.84
    </h1>
    -2.70
    </h3>
    -2.58
     если
    -2.56
    </u>
    -2.41
     も
    -2.39
    </th>
    -2.36
     ,
    -2.33
    POSITIVE LOGITS
    ’,
    3.20
     剧照
    2.83
    鹟
    2.81
     lada
    2.72
     ftate
    2.69
     gita
    2.66
     parachoque
    2.64
    毟
    2.63
     diza
    2.63
     luka
    2.59
    Activations Density 0.001%

    No Known Activations