© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12890
    Prev
    Next
    INDEX
    Explanations

    animals and related mythological creatures

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

    This neuron detects named entities—proper nouns such as organization, brand, or location names.

    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_31_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
     অভিব্য
    0.64
    ቃዎች
    0.64
     magenta
    0.60
    第壹百
    0.60
     linguistic
    0.59
    STRUCTIONS
    0.59
     ঠ
    0.56
     paraf
    0.56
    याँ
    0.56
     Booklet
    0.55
    POSITIVE LOGITS
    roar
    0.81
    🐯
    0.80
    Lion
    0.76
     lion
    0.76
    狮
    0.74
    🐅
    0.73
    bear
    0.72
    🦈
    0.72
     roar
    0.71
    🦁
    0.71
    Activations Density 0.249%

    No Known Activations