© 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. 58263
    Prev
    Next
    INDEX
    Explanations

    box office

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

    The neuron activates on mentions of “box office” (and associated numeric figures), i.e. references to box office performance.

    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
    ’
    -2.34
    </h5>
    -2.09
    phoric
    -1.88
    </td>
    -1.83
     that
    -1.82
    </i>
    -1.77
    </tr>
    -1.76
     =
    -1.75
    ”,
    -1.75
     —
    -1.73
    POSITIVE LOGITS
    )--
    1.90
    homonymie
    1.83
    Begriffsklä
    1.76
     néhány
    1.71
    だったので
    1.68
     Heilige
    1.59
    zmm
    1.59
    ﮯ
    1.57
    棰
    1.55
     Национальный
    1.53
    Activations Density 0.005%

    No Known Activations