© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9292
    Prev
    Next
    INDEX
    Explanations

    walking, jogging, hiking

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

    The neuron responds to words describing modes of physical movement (e.g. walking, kayaking, riding, floating).

    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
    ד
    0.94
    ล็อก
    0.84
    мі
    0.82
    Drawer
    0.82
    ोदर
    0.82
    ра
    0.82
    स्करी
    0.81
    ล
    0.81
    ্যস্ত
    0.80
     satirical
    0.79
    POSITIVE LOGITS
    and
    1.11
    婵
    0.91
    ikler
    0.86
    雩
    0.84
    एंगे
    0.83
     Veľ
    0.82
    k
    0.82
    ಿಗಳ
    0.81
    Tenemos
    0.80
     Chiến
    0.80
    Activations Density 0.919%

    No Known Activations