© 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. 129819
    Prev
    Next
    INDEX
    Explanations

    symbols in code and math

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

    The neuron activates on numeric literals (constants) in code.

    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
     again
    -1.63
     only
    -1.47
     from
    -1.41
     five
    -1.32
     dentelle
    -1.28
    蜒
    -1.23
    miendo
    -1.23
    秩
    -1.20
     управління
    -1.19
     】
    -1.16
    POSITIVE LOGITS
     we
    1.79
    }(\
    1.24
    بعض
    1.13
     vengono
    1.13
     alguns
    1.12
    çim
    1.09
    鐽
    1.06
     fournis
    1.05
    做
    1.05
     abbiamo
    1.04
    Activations Density 0.071%

    No Known Activations