© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    core

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

    This neuron detects emphatic noun phrases introduced by “The” (e.g. “The point,” “The weakness,” “The nature,” etc.).

    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
    /
    0.60
    。
    0.60
    0.58
    0.55
                              
    0.54
                      
    0.53
                          
    0.53
    Weblinks
    0.53
              
    0.52
    }
    0.52
    POSITIVE LOGITS
     uptick
    0.75
     result
    0.66
     результат
    0.66
     नतीजा
    0.66
    ﻴ
    0.65
     onslaught
    0.64
     indictment
    0.63
     результатом
    0.62
     epitome
    0.61
     dichotomy
    0.59
    Activations Density 0.053%

    No Known Activations