© 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. 4449
    Prev
    Next
    INDEX
    Explanations

    challenges and compatibility

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

    The neuron activates on numeric tokens with 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
     ganz
    0.78
     ganzen
    0.73
     Freeman
    0.71
     trotzdem
    0.70
    UMBIA
    0.69
    드
    0.69
     swore
    0.66
     variedade
    0.66
     Saltar
    0.66
    ーク
    0.66
    POSITIVE LOGITS
    ments
    0.84
    ूत
    0.80
    mute
    0.78
    Eau
    0.77
    股市
    0.76
    衝撃
    0.75
     空
    0.75
    muse
    0.74
    ከና
    0.73
    غر
    0.73
    Activations Density 0.000%

    No Known Activations