© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3457
    Prev
    Next
    INDEX
    Explanations

    war in Ukraine

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

    This neuron detects mentions of specific named entities—especially country/region names, political organizations, or key place/people proper nouns.

    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
     or
    0.79
     nebo
    0.65
     혹은
    0.63
     hoặc
    0.63
     atau
    0.59
    หรือ
    0.59
     T
    0.58
     oder
    0.58
     또는
    0.57
     eller
    0.55
    POSITIVE LOGITS
     парламент
    0.58
     నేపథ్యంలో
    0.57
    terrorism
    0.56
     кризи
    0.56
    czyny
    0.55
    <unused0>
    0.55
    harusnya
    0.55
     आतंकवादी
    0.54
     президента
    0.53
     विधेयक
    0.53
    Activations Density 0.001%

    No Known Activations