© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112155
    Prev
    Next
    INDEX
    Explanations

    cost of

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

    The neuron strongly activates on “of” (and surrounding words) in cost‐related expressions—i.e. it detects “cost of …” and other monetary‐amount contexts.

    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
     also
    -1.91
     corazon
    -1.88
     africano
    -1.87
    The
    -1.85
     animasi
    -1.84
     .'
    -1.83
     baka
    -1.82
     accommodates
    -1.80
     governs
    -1.80
     kazak
    -1.77
    POSITIVE LOGITS
     avec
    2.08
    with
    1.88
     is
    1.76
     wichtigsten
    1.73
     Verpflich
    1.70
     vand
    1.68
    ников
    1.67
     ไม่มี
    1.67
    ates
    1.66
     browning
    1.66
    Activations Density 0.007%

    No Known Activations