© 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. 5164
    Prev
    Next
    INDEX
    Explanations

    consumer or producer

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

    The neuron is keyed to floating‐point numbers (i.e. numerical values with decimal points).

    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
    杆
    0.82
     服务器
    0.80
     సి
    0.75
    法
    0.74
     WORKS
    0.72
    服务器
    0.71
    畊
    0.71
    ზ
    0.70
    ସ
    0.69
     Andrey
    0.69
    POSITIVE LOGITS
     eigene
    0.82
     fuori
    0.79
     grazie
    0.75
     tendo
    0.74
     álgebra
    0.73
     debido
    0.72
    ются
    0.72
     assim
    0.72
     malignancies
    0.70
     globale
    0.70
    Activations Density 0.004%

    No Known Activations