© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9160
    Prev
    Next
    INDEX
    Explanations

    add_attribute, generate_odd_numbers, extract_numbers, remove_dir

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

    The neuron fires on the section‐heading tokens in code or API documentation (e.g. “Returns,” “Error —,” field or object labels) that introduce descriptive blocks.

    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
    Y
    0.93
    YOU
    0.93
    1
    0.92
    Vol
    0.91
        
    0.89
    7
    0.89
    B
    0.88
    G
    0.87
    E
    0.86
    私は
    0.86
    POSITIVE LOGITS
     {@
    1.20
     encapsulates
    1.12
     Represents
    1.11
     Provides
    1.08
     identifies
    1.07
     initializes
    1.06
     Describes
    1.06
     describes
    1.00
     ہے۔
    0.98
     Specifies
    0.96
    Activations Density 0.069%

    No Known Activations