© 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. 8809
    Prev
    Next
    INDEX
    Explanations

    if clauses and lists

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

    The neuron activates on floating‐point numeric tokens (numbers with decimal points).

    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
    I
    0.81
    ؤ
    0.80
    Ele
    0.79
    kon
    0.79
    i
    0.77
    0
    0.77
    cuno
    0.75
    k
    0.74
    t
    0.73
    p
    0.70
    POSITIVE LOGITS
    θηκε
    0.92
    рный
    0.85
     деятельность
    0.83
    ᠶ
    0.82
     predicate
    0.81
    तेला
    0.81
    OLYBD
    0.80
     большое
    0.80
     signifying
    0.80
    ങ്
    0.79
    Activations Density 0.000%

    No Known Activations