© 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. 2590
    Prev
    Next
    INDEX
    Explanations

    and incubi

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

    This neuron fires on biological or anatomical terms—names of animals, body parts, and demographic/gender 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
    ईद
    0.67
    ع
    0.52
    服务
    0.51
    irinha
    0.51
    κέ
    0.50
     épisode
    0.49
     πολλά
    0.49
     pelayanan
    0.48
    Hig
    0.48
     wacht
    0.48
    POSITIVE LOGITS
     ()
    0.60
    uminium
    0.49
     ())
    0.48
     respectively
    0.47
     ():
    0.47
     보유
    0.47
     granule
    0.46
    ermost
    0.46
    /(
    0.45
     pathogenic
    0.45
    Activations Density 0.000%

    No Known Activations