© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    iran israel retaliatory strikes

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

    The neuron responds strongest to named entities—proper names of people, places, organizations, and similar capitalized terms.

    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
     ඔබට
    0.49
    SS
    0.47
    LAW
    0.46
     หรือ
    0.43
    N
    0.43
    T
    0.42
     seront
    0.42
     Pres
    0.42
     Hob
    0.41
     law
    0.41
    POSITIVE LOGITS
     owing
    0.67
     omdat
    0.63
     vanwege
    0.58
     bolstering
    0.57
     debido
    0.56
     because
    0.55
     akibat
    0.54
    due
    0.54
    ∵
    0.54
     έναν
    0.53
    Activations Density 0.003%

    No Known Activations