© 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. 6094
    Prev
    Next
    INDEX
    Explanations

    technical concepts and systems

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

    The neuron selectively activates on domain‐specific content words—especially proper nouns or technical terms.

    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
    であるが
    0.65
    のですが
    0.64
    żenia
    0.60
    などは
    0.60
    非常的
    0.59
     වන්නේ
    0.58
    は
    0.57
    なのですが
    0.57
    单独
    0.56
    வான
    0.55
    POSITIVE LOGITS
     ताकि
    0.70
    .“
    0.61
     nhằm
    0.61
     amid
    0.60
     تاکہ
    0.59
    .</
    0.59
     fibrils
    0.58
     empêcher
    0.56
    .”
    0.55
    .​​
    0.55
    Activations Density 0.004%

    No Known Activations