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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5449
    Prev
    Next
    INDEX
    Explanations

    error handling with try except

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

    The neuron is triggered by floating‐point numerical tokens (decimal numbers) in the text.

    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_24_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
    aea
    0.81
    בודה
    0.80
    𝐃
    0.74
    Boa
    0.73
     transgene
    0.73
    ATIVA
    0.72
    नंतर
    0.71
    бера
    0.71
    DHT
    0.71
     ambientale
    0.71
    POSITIVE LOGITS
    ك
    0.82
     salient
    0.81
    ى
    0.80
     စ
    0.80
     Autoren
    0.79
     Ե
    0.79
    dominant
    0.78
    striped
    0.75
     Ս
    0.74
    علي
    0.74
    Activations Density 0.000%

    No Known Activations