© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11434
    Prev
    Next
    INDEX
    Explanations

    `via`, `spark`, `whether`, `me`, `captivated`, `having`, `attracted`, `yet`, `given`

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

    The neuron specifically detects numeric tokens that are floating-point values (i.e. numbers containing a decimal point).

    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
    ла
    0.86
    ли
    0.84
     blanches
    0.75
    █
    0.75
    JACK
    0.73
    مق
    0.73
     Hardly
    0.72
     sinned
    0.70
    									
    0.70
    profitable
    0.69
    POSITIVE LOGITS
     haremos
    0.85
     lectores
    0.82
     fijo
    0.81
    ṱ
    0.80
    ailand
    0.79
     rojos
    0.79
     suyo
    0.79
     mismos
    0.78
    DanhMuc
    0.78
     mensuales
    0.78
    Activations Density 0.000%

    No Known Activations