© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6847
    Prev
    Next
    INDEX
    Explanations

    reducing or overcoming dependency

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

    The neuron activates on terms describing interpersonal or animal‐human interaction behaviors (e.g. learning boundaries, submissiveness, expressing displeasure).

    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
    Notwithstanding
    1.08
     sämt
    1.01
    либо
    0.90
    あるいは
    0.84
    に関する
    0.82
    Numerous
    0.81
    Blockchain
    0.80
    を有する
    0.80
    優れた
    0.77
    Owing
    0.77
    POSITIVE LOGITS
     new
    1.04
     nový
    1.00
     changed
    0.96
     बदलाव
    0.96
     stillness
    0.93
     trochu
    0.92
     변화
    0.91
     calmed
    0.90
     two
    0.89
     nowy
    0.89
    Activations Density 0.143%

    No Known Activations