© 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. 6792
    Prev
    Next
    INDEX
    Explanations

    me know

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

    The neuron strongly activates on the contraction “I’ll,” i.e. first‐person future (“I will”).

    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
    したいと思います
    0.84
     посмотрим
    0.77
     বলার
    0.73
    😉
    0.70
     اتمنى
    0.68
    让我
    0.67
    😊
    0.66
    😁
    0.66
     গিয়েছিলাম
    0.66
     вспом
    0.66
    POSITIVE LOGITS
     vervolgens
    0.77
     нередко
    0.69
     fréquemment
    0.68
     variously
    0.68
     ofte
    0.67
     tzv
    0.66
     часто
    0.66
     professed
    0.65
     genellikle
    0.65
     gyak
    0.65
    Activations Density 0.115%

    No Known Activations