© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45495
    Prev
    Next
    INDEX
    Explanations

    email inbox

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

    The main thing this neuron does is detect the word “inbox” (i.e. references to an email inbox).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    </strong>
    -3.11
    </u>
    -3.05
    </h3>
    -2.95
    ,’
    -2.63
    </sub>
    -2.58
    และ
    -2.45
    </i>
    -2.44
    %;
    -2.31
    ";
    -2.28
    她
    -2.28
    POSITIVE LOGITS
    这件事情
    2.45
    ing
    2.36
     In
    2.36
     disfruta
    2.31
    櫺
    2.23
     Both
    2.22
     BOTH
    2.19
     reconocido
    2.14
    此事
    2.08
     éditoriale
    2.06
    Activations Density 0.002%

    No Known Activations