© 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. 5111
    Prev
    Next
    INDEX
    Explanations

    tensorflow, python, repos, fibrosis

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

    The neuron activates on numeric tokens—especially floating‐point numbers.

    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
     αυτό
    0.91
     ช่วง
    0.87
     único
    0.82
    
    0.82
     จุด
    0.80
     solcher
    0.80
     festgestellt
    0.79
    atributo
    0.76
     weiterer
    0.75
     nedeniyle
    0.75
    POSITIVE LOGITS
    怙
    0.84
    examine
    0.77
    넬
    0.77
    ྦ
    0.75
    وى
    0.74
    جيل
    0.73
    نين
    0.72
    WHY
    0.72
    Existence
    0.72
    K
    0.72
    Activations Density 0.000%

    No Known Activations