© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6029
    Prev
    Next
    INDEX
    Explanations

    all followed by noun or slash

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

    This neuron detects “See all”/“Read all” (e.g. “See all 2582…,” “Read all 1781…”) calls to view or list all items.

    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
     Nell
    0.64
     控制
    0.64
    ፈጥ
    0.58
     利
    0.57
     さ
    0.57
    plas
    0.56
     David
    0.56
    ogen
    0.55
     Möglich
    0.55
     Alec
    0.54
    POSITIVE LOGITS
     cinn
    0.61
    に進
    0.55
     radiate
    0.55
    сур
    0.53
     миро
    0.52
    লম্ব
    0.52
     décou
    0.51
    瘋
    0.51
     resembled
    0.50
     wholeheartedly
    0.50
    Activations Density 0.000%

    No Known Activations