© 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. 16217
    Prev
    Next
    INDEX
    Explanations

    class definitions, local execution

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

    This neuron fires on floating‐point numeric literals (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
    ρική
    0.85
    والفقار
    0.79
    acciones
    0.76
    antica
    0.75
    nikom
    0.74
    𝒶
    0.73
    ích
    0.73
    alunos
    0.73
    zieh
    0.72
    prevState
    0.72
    POSITIVE LOGITS
    Fe
    0.83
     constitu
    0.79
    ','
    0.76
    Csvg
    0.76
    '
    0.75
     details
    0.75
     resolver
    0.75
     claire
    0.75
    }])
    0.75
     offer
    0.74
    Activations Density 0.000%

    No Known Activations