© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    row and column structures

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

    The neuron strongly activates on numeric tokens containing decimal points (i.e. 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
    ంబే
    0.84
     使っ
    0.79
     אח
    0.78
     bolje
    0.75
    勵
    0.75
     اثنين
    0.74
    ន្ទ
    0.72
     акы
    0.72
    NESOTA
    0.70
     دیے
    0.70
    POSITIVE LOGITS
    󠁢
    0.77
    夏
    0.75
    乱流
    0.73
     Festivals
    0.72
    部分
    0.71
     Passion
    0.70
     Sexual
    0.69
     Advances
    0.69
     Distillery
    0.69
     Shallow
    0.69
    Activations Density 0.000%

    No Known Activations