© 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. 3076
    Prev
    Next
    INDEX
    Explanations

    obviously, course, naturally

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

    The neuron strongly activates on the discourse marker “Of course,” indicating it’s looking for that specific transition phrase.

    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
    甚至
    0.90
    <0x94>
    0.74
     thậm
    0.72
    ">-->
    0.71
    od
    0.69
     khoảng
    0.69
    ding
    0.67
    مين
    0.67
     Giáo
    0.67
    
    0.66
    POSITIVE LOGITS
     당연
    1.48
     obviamente
    1.34
     évidemment
    1.30
     oczywiście
    1.30
     ovviamente
    1.29
     natürlich
    1.24
     当然
    1.16
    もちろん
    1.14
     конечно
    1.11
     natuurlijk
    1.10
    Activations Density 0.143%

    No Known Activations