© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1187
    Prev
    Next
    INDEX
    Explanations

    family relationships and connections

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

    The neuron strongly activates on large numeric tokens—i.e. unusually big numbers or figures.

    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
    判断
    0.55
    '></
    0.54
    粽
    0.50
     пло
    0.50
    По
    0.49
     если
    0.49
     подходя
    0.49
     отверсти
    0.49
    iyoruz
    0.48
    焼
    0.48
    POSITIVE LOGITS
    ،
    0.91
     Emeritus
    0.86
     Robert
    0.80
     extraordinaire
    0.77
    ፣
    0.77
     yakni
    0.76
     namely
    0.75
     Michael
    0.74
     Charles
    0.74
     Mike
    0.73
    Activations Density 0.106%

    No Known Activations