© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5632
    Prev
    Next
    INDEX
    Explanations

    programming code structure

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

    The neuron fires strongly on capitalized proper names, product or project names, and other named entities or identifiers.

    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
    In
    0.64
     acest
    0.61
    It
    0.59
    H
    0.59
    Econom
    0.58
    Wire
    0.57
    ANU
    0.57
     In
    0.56
     आणि
    0.56
     هذه
    0.56
    POSITIVE LOGITS
     punya
    0.62
    最大的
    0.56
    全体の
    0.56
    getQuery
    0.56
    的第一
    0.55
    における
    0.55
     objectForKey
    0.54
     دارای
    0.54
     valueForKey
    0.53
    的一
    0.53
    Activations Density 0.332%

    No Known Activations