© 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. 8745
    Prev
    Next
    INDEX
    Explanations

    soaked ladyfingers

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

    The neuron flags interface or call-to-action cues—especially mentions of “links,” “below,” and similar prompt words directing the reader to click, follow, or share.

    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
     ткань
    0.74
    invention
    0.70
    estas
    0.69
    防御
    0.68
    +'
    0.67
    になって
    0.67
     ഹി
    0.67
    وامی
    0.67
    しかも
    0.66
    να
    0.66
    POSITIVE LOGITS
     sollic
    0.75
    ங்களின்
    0.68
     setbacks
    0.67
     stabilizers
    0.65
    ো
    0.65
     sobri
    0.65
     graz
    0.64
     séries
    0.63
     sconf
    0.63
     grizzly
    0.62
    Activations Density 0.000%

    No Known Activations