© 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. 83868
    Prev
    Next
    INDEX
    Explanations

    building relationships

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

    This neuron detects mentions of relationships and related terms (e.g. “relationships,” “develop relationships,” “manage vendor relationships”).

    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
     a
    -1.82
     lustige
    -1.81
    </em>
    -1.57
    unikasi
    -1.56
    狳
    -1.55
     Werken
    -1.52
    蟥
    -1.51
     uitzicht
    -1.48
    獴
    -1.48
    cepatan
    -1.47
    POSITIVE LOGITS
    R
    1.80
    }
    1.77
     навіть
    1.54
     will
    1.52
    I
    1.48
    гії
    1.48
     mereka
    1.45
    Таким
    1.44
    Сти
    1.43
    C
    1.41
    Activations Density 0.017%

    No Known Activations