© 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. 656
    Prev
    Next
    INDEX
    Explanations

    ready or committed to action

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

    The neuron strongly activates on occurrences of the first-person singular pronoun “I.”

    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
    げ
    0.39
    唔
    0.38
     bilmi
    0.37
    啥
    0.36
     जाओ
    0.36
    삿
    0.35
    哂
    0.35
    pokemon
    0.35
    囔
    0.35
    goog
    0.35
    POSITIVE LOGITS
     multidis
    0.49
     empowers
    0.47
     pioneering
    0.46
     embodies
    0.45
     посредством
    0.44
     collaborates
    0.43
     enables
    0.43
     collaboratively
    0.42
    ເພື່ອ
    0.42
     establishes
    0.41
    Activations Density 0.000%

    No Known Activations