© 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. 6525
    Prev
    Next
    INDEX
    Explanations

    rhythm

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

    The neuron strongly activates on named-entity tokens—proper names, acronyms, bylines, and similar capitalized identifiers.

    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
     قي
    0.55
     পরাজিত
    0.54
    腓
    0.54
    elope
    0.53
    MAIL
    0.50
     छोड़
    0.50
    区间
    0.50
     القي
    0.49
    Princeton
    0.49
    咽
    0.49
    POSITIVE LOGITS
     preparar
    0.62
    versible
    0.57
     estamos
    0.53
     Turismo
    0.53
     Raut
    0.53
     frag
    0.53
    ustible
    0.52
     :-
    0.52
     coordinators
    0.52
     avance
    0.51
    Activations Density 0.044%

    No Known Activations