© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10260
    Prev
    Next
    INDEX
    Explanations

    action phrases followed by placeholders

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

    The neuron fires on extended spans of direct speech or long quoted passages.

    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_31_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
     "
    0.79
     “
    0.68
    所谓的
    0.66
    ​
    0.66
    可谓
    0.63
     appunto
    0.63
    单纯
    0.61
     സ്വന്ത
    0.58
    Ironically
    0.57
    所谓
    0.57
    POSITIVE LOGITS
     XYZ
    1.66
     xyz
    1.62
     _______
    1.52
     xxx
    1.51
     ______
    1.46
     XXX
    1.45
     _____
    1.45
    XXXX
    1.35
     ____
    1.35
     blah
    1.35
    Activations Density 0.280%

    No Known Activations