© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    people and their names

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

    This neuron is effectively “dead” – it never activates and doesn’t pick out any particular tokens or patterns.

    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
    schedule
    0.58
    LocalDateTime
    0.56
    ++++++++++++++++
    0.55
    ===============
    0.54
    createNew
    0.54
    userService
    0.53
    todo
    0.53
    summary
    0.52
    image
    0.52
    definition
    0.51
    POSITIVE LOGITS
     extremity
    0.55
     ใช่
    0.55
     ทำให้
    0.54
     espè
    0.52
     โดย
    0.51
     ngunit
    0.51
     แต่
    0.51
     phenotypes
    0.49
    ‌ನ
    0.48
     presidents
    0.47
    Activations Density 0.198%

    No Known Activations