© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    from X to Y

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

    This neuron activates on numeric tokens containing decimal points (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
    ι
    0.78
    żeń
    0.77
     maisons
    0.75
     modifié
    0.74
     médian
    0.73
     ditampilkan
    0.73
     nein
    0.72
    栝
    0.72
    ものの
    0.71
    TERS
    0.71
    POSITIVE LOGITS
     ومن
    1.06
    0
    0.94
     afar
    0.90
     standpoint
    0.88
    into
    0.80
     طریق
    0.70
     ומ
    0.70
    일을
    0.70
    Emphasis
    0.69
     मौ
    0.68
    Activations Density 0.038%

    No Known Activations