© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    per depositor, per bank

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

    The neuron is sensitive to numeric tokens—especially decimal or statistical values—spotting numbers and measurements 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
    ת
    0.90
    }');
    0.84
    ্লাহ
    0.84
    ণ
    0.84
    સ
    0.81
    腈
    0.79
    Стра
    0.78
     rétrécies
    0.77
     basilaires
    0.76
     タイヤ
    0.75
    POSITIVE LOGITS
    ed
    0.88
    ды
    0.87
    довой
    0.85
     respeito
    0.80
    o
    0.78
    hots
    0.77
    ously
    0.77
     bagels
    0.75
    oid
    0.75
    urs
    0.75
    Activations Density 0.000%

    No Known Activations