© 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. 6319
    Prev
    Next
    INDEX
    Explanations

    average, metrics, performance

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

    The neuron activates on numeric tokens representing measured or statistical values (e.g., floating‐point numbers and p-values).

    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
     કંઈ
    0.70
    약
    0.64
    海外
    0.63
     भेज
    0.63
    something
    0.63
     Ceux
    0.62
    Can
    0.62
    約
    0.60
    said
    0.59
     ilyen
    0.59
    POSITIVE LOGITS
     rendimiento
    0.85
     NOx
    0.83
     performance
    0.82
     efficiency
    0.80
     RMSE
    0.78
     metrics
    0.78
     reactivity
    0.78
     ratios
    0.77
     percentage
    0.77
     cortisol
    0.76
    Activations Density 0.083%

    No Known Activations