© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    approximate or estimate values

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

    The neuron primarily fires on numeric expressions and measurements (numbers and their associated units) in the text.

    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
    ется
    1.11
    ן
    1.11
     अभिनय
    1.09
    ла
    1.08
     وإ
    1.08
     آن
    1.07
    ته
    1.06
     seul
    1.05
    тая
    1.03
     וע
    1.02
    POSITIVE LOGITS
    roughly
    1.55
     Roughly
    1.27
     roughly
    1.20
     Reprinted
    1.20
    엷
    1.14
    s
    1.13
     around
    1.11
    看看
    1.11
    Lovely
    1.11
    idée
    1.11
    Activations Density 1.763%

    No Known Activations