© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71722
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and question labels

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

    The neuron activates on the LaTeX “\partial” tokens—that is, occurrences of the partial‐derivative symbol.

    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
    .
    -1.95
    宬
    -1.58
    cosas
    -1.51
     him
    -1.51
     místa
    -1.50
     Anſ
    -1.48
     naší
    -1.41
    Ꮸ
    -1.41
    dä
    -1.41
     Inſ
    -1.40
    POSITIVE LOGITS
    5
    2.39
    2
    2.23
    6
    2.17
    3
    2.09
    }
    2.00
    7
    1.99
    4
    1.99
    .
    1.86
        
    1.84
    ↵
    1.81
    Activations Density 0.002%

    No Known Activations