© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8585
    Prev
    Next
    INDEX
    Explanations

    This is the

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

    This neuron fires on the very first content token at the start of each new text block.

    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
    ุป
    0.50
    Knowing
    0.50
         
    0.50
     diffé
    0.49
      
    0.49
    ுமி
    0.48
    agę
    0.48
    >;
    0.47
    ieważ
    0.47
     berb
    0.47
    POSITIVE LOGITS
     been
    1.45
     gonna
    1.44
     blevet
    1.43
     blitt
    1.30
    been
    1.27
     afraid
    1.26
     ollut
    1.23
     fått
    1.22
     able
    1.20
     unable
    1.20
    Activations Density 0.358%

    No Known Activations