© 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. 5057
    Prev
    Next
    INDEX
    Explanations

    modelmodel numbers and identifiers

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

    The neuron fires strongly on standalone numeric tokens (e.g. two‐digit model or spec 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
    7
    0.40
     n
    0.40
    1
    0.40
    3
    0.39
    Y
    0.39
    ol
    0.38
    夋
    0.38
     Y
    0.38
     Saccharomyces
    0.38
     Seven
    0.37
    POSITIVE LOGITS
    ຜະລິດຕ
    0.41
     pracę
    0.37
     যোদ্ধা
    0.36
     устрой
    0.36
    прода
    0.35
    💰
    0.35
     kullanım
    0.34
    passen
    0.34
     persen
    0.34
     রাজশ
    0.34
    Activations Density 0.001%

    No Known Activations