© 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. 10-GEMMASCOPE-RES-131K
    7. 1882
    Prev
    Next
    INDEX
    Explanations

    this week

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

    The neuron responds to the word “week” (especially in recurring‐segment headings like “This week” or “This week’s”).

    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
    –
    -1.72
    }
    -1.67
    すぐに
    -1.66
     instrucción
    -1.66
    ’
    -1.64
     prerequisites
    -1.58
    '
    -1.56
    牁
    -1.56
    jenigen
    -1.55
    那些
    -1.50
    POSITIVE LOGITS
     были
    1.86
     concluye
    1.77
     sebagai
    1.77
    </tfoot>
    1.71
     descubre
    1.69
     déput
    1.66
     disfruta
    1.60
     láser
    1.58
     rodea
    1.51
    1.51
    Activations Density 0.017%

    No Known Activations