© 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. 5318
    Prev
    Next
    INDEX
    Explanations

    numbers

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

    The neuron fires on references to network packet‐filtering rules, especially adapter names and IP‐address patterns.

    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
    來
    0.61
    来
    0.57
    ank
    0.54
    Origin
    0.52
    所以
    0.51
    H
    0.50
    ch
    0.50
    が
    0.49
    形
    0.49
    versus
    0.49
    POSITIVE LOGITS
     다양한
    0.76
    ,
    0.69
     ressent
    0.68
     Nemours
    0.66
     낮은
    0.66
     עם
    0.65
     પરંતુ
    0.65
     quarts
    0.64
     ፣
    0.63
     αλλά
    0.63
    Activations Density 0.047%

    No Known Activations