© 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. 4806
    Prev
    Next
    INDEX
    Explanations

    barroco, read endpoint, data layer push

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

    The neuron is activated by floating-point numeric values (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
    IN
    0.75
    ક
    0.71
    シンプルな
    0.71
    ä
    0.68
    ien
    0.66
    ことなく
    0.66
    のが
    0.65
    wać
    0.64
    ږي
    0.64
     donnant
    0.64
    POSITIVE LOGITS
     DSF
    0.93
     MFP
    0.92
     двух
    0.80
     Myrtle
    0.79
    兩
    0.78
     delt
    0.77
     burrito
    0.76
     fieldwork
    0.76
     seagulls
    0.75
    五
    0.75
    Activations Density 0.001%

    No Known Activations