© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7264
    Prev
    Next
    INDEX
    Explanations

    agents and support

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

    The neuron activates on floating-point numeric tokens (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
    otricha
    0.89
     生地
    0.88
     우리는
    0.82
     Ngoài
    0.82
     ใส่
    0.81
    $\--
    0.81
    istors
    0.80
    ótica
    0.80
    iliği
    0.79
    rawberry
    0.79
    POSITIVE LOGITS
     entirety
    0.83
     unwavering
    0.83
     a
    0.79
     irrevoc
    0.79
     cybersecurity
    0.78
     egregious
    0.77
     any
    0.75
     certain
    0.75
     meticulous
    0.75
     grueling
    0.75
    Activations Density 0.001%

    No Known Activations