© 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. 13501
    Prev
    Next
    INDEX
    Explanations

    Microsoft Copilot

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

    The neuron fires on numeric values expressed with decimal points.

    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
     attire
    0.86
     ornamentation
    0.82
     utilize
    0.82
     नही
    0.82
     necessitating
    0.79
    丝毫
    0.79
     রহিল
    0.77
    扨
    0.77
     replete
    0.76
     परिवर्तित
    0.75
    POSITIVE LOGITS
     ámbitos
    0.77
     CRISPR
    0.76
    𝐂
    0.74
     Москвы
    0.72
     NLRP
    0.71
    喺
    0.71
     コンパクト
    0.71
     핵심
    0.71
    ⃛
    0.70
    めっちゃ
    0.70
    Activations Density 0.005%

    No Known Activations