© 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. 12623
    Prev
    Next
    INDEX
    Explanations

    oral stimulation

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

    This neuron fires on proper names or unique entities (e.g., brand, product, or specialist names).

    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
    .
    0.85
     arable
    0.80
     weer
    0.77
    ia
    0.76
     carc
    0.74
     tin
    0.73
    ции
    0.72
     refor
    0.72
    os
    0.71
     teore
    0.71
    POSITIVE LOGITS
     长
    0.73
    霑
    0.71
     遊
    0.69
    developing
    0.68
    ून्य
    0.67
    Ά
    0.67
    飜
    0.67
     início
    0.65
    Namun
    0.65
    𝗷
    0.65
    Activations Density 0.000%

    No Known Activations