© 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. 10728
    Prev
    Next
    INDEX
    Explanations

    section headers or specific tokens

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

    The neuron fires on numeric expressions (decimal or integer values) in mathematical 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
     "
    -2.06
    </sup>
    -2.02
     on
    -1.92
     To
    -1.92
     Only
    -1.90
     From
    -1.87
    </th>
    -1.86
     I
    -1.83
     That
    -1.82
     The
    -1.77
    POSITIVE LOGITS
    殽
    2.13
    afficher
    1.98
    
    1.95
    擽
    1.92
     camiset
    1.91
    🆗
    1.90
    ჱ
    1.89
    龵
    1.88
    Reak
    1.84
    affichage
    1.84
    Activations Density 0.006%

    No Known Activations