© 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. 2103
    Prev
    Next
    INDEX
    Explanations

    list formatting and special characters

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

    The main thing this neuron does is detect numeric specifications and measurements (e.g. dimensions, capacities, and other technical units).

    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
     finalizar
    0.60
     mümkün
    0.59
     Lastly
    0.59
    चुरी
    0.58
     最後
    0.57
     {}'.
    0.56
    மாகும்
    0.56
    cektir
    0.56
    শেষে
    0.56
     lastly
    0.56
    POSITIVE LOGITS
    0.60
    ;
    0.58
    ¦
    0.57
    ├
    0.53
    、、
    0.52
    Second
    0.51
    」「
    0.51
     deuxième
    0.51
    A
    0.50
         
    0.49
    Activations Density 0.298%

    No Known Activations