© 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. 9187
    Prev
    Next
    INDEX
    Explanations

    target for babies

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

    The main thing this neuron does is detect floating-point numbers (decimal numerical values) 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
    Chia
    0.88
    B
    0.78
    𝗕
    0.70
    Bub
    0.69
    َد
    0.68
    ़
    0.67
    🄴
    0.67
    <h4>
    0.64
    BO
    0.64
    Situated
    0.64
    POSITIVE LOGITS
    agian
    0.89
    ocere
    0.86
     symbolically
    0.84
    hInstance
    0.81
     casket
    0.80
    weds
    0.79
     sakura
    0.79
     porches
    0.78
     जिसे
    0.77
     simbol
    0.77
    Activations Density 0.000%

    No Known Activations