© 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. 13974
    Prev
    Next
    INDEX
    Explanations

    physics, AI, programming, spreadsheets

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

    The neuron identifies salient topic-carrying words (especially key nouns and proper nouns) that signal what the current passage is about.

    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
     entanglement
    0.80
    仕事
    0.77
    ન્
    0.76
    sunline
    0.76
    六
    0.74
    ステンレス
    0.73
    ঈশ্বর
    0.73
    轶
    0.73
    潜在
    0.72
    Tìm
    0.71
    POSITIVE LOGITS
    ية
    0.97
     c
    0.86
     Sy
    0.86
     p
    0.81
     W
    0.79
     एंड
    0.79
     And
    0.79
     बू
    0.79
     J
    0.78
     B
    0.78
    Activations Density 0.000%

    No Known Activations