© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7223
    Prev
    Next
    INDEX
    Explanations

    punctuation and connectors

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

    The main thing this neuron does is detect numeric values or measurements (e.g. digits, quantities, and scales).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ––
    0.99
     ≈
    0.97
    ‒
    0.91
     ʻ
    0.86
    ½
    0.82
     │
    0.80
     præ
    0.79
     până
    0.79
     naï
    0.78
     naïve
    0.78
    POSITIVE LOGITS
     उन्ह
    1.34
     अा
    1.30
     ে
    1.28
     ि
    1.25
     ofthe
    1.21
    誢
    1.20
    旪
    1.19
    僟
    1.18
     которы
    1.17
     Univer
    1.16
    Activations Density 0.477%

    No Known Activations