© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14851
    Prev
    Next
    INDEX
    Explanations

    copy right

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

    The neuron detects explicit numerical values and metrics (e.g., counts, percentages, and quantitative measures) in the text.

    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
     González
    0.86
    3
    0.85
    6
    0.82
     López
    0.82
     Díaz
    0.80
     ét
    0.79
     Pérez
    0.77
     రు
    0.76
     convolutional
    0.74
     missiles
    0.73
    POSITIVE LOGITS
     ধারনা
    1.20
     부터
    1.09
     loosing
    1.08
     ব্যার্থ
    1.06
     युवाओ
    1.05
    ttes
    1.00
    ॔
    1.00
     dimana
    0.99
     महिलाओ
    0.99
     অনুয
    0.98
    Activations Density 1.763%

    No Known Activations