© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    Once you provide

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

    The neuron detects four-digit numeric tokens representing years or date stamps 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
    asyon
    1.17
    这次
    1.15
    这
    1.11
    
    1.10
    }$
    1.09
     ntawm
    1.09
    ્સ
    1.09
     Mikolai
    1.08
    CLASSES
    1.05
    𝗻
    1.05
    POSITIVE LOGITS
     excret
    1.24
     aficionados
    1.15
     transmittance
    1.15
     এদিকে
    1.14
     arre
    1.13
     intrusions
    1.13
    ylated
    1.13
     cuddle
    1.11
     delinqu
    1.10
     interoper
    1.09
    Activations Density 0.019%

    No Known Activations