© 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. 6712
    Prev
    Next
    INDEX
    Explanations

    circularity and loops

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

    The neuron fires on words describing circular shapes or motions (e.g. ring, circle, vortex, circling, centered).

    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
     lading
    0.50
     Rough
    0.49
    ▮
    0.49
    жити
    0.49
     তাড়
    0.48
    讠
    0.48
    glRaster
    0.48
    менный
    0.48
     Mascot
    0.47
     sneeze
    0.47
    POSITIVE LOGITS
     вокруг
    2.28
     circumference
    2.11
     autour
    2.09
    环
    2.09
     encir
    2.06
     attorno
    2.03
     around
    2.00
    環
    1.98
    圈
    1.98
     ring
    1.94
    Activations Density 0.528%

    No Known Activations