© 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. 8411
    Prev
    Next
    INDEX
    Explanations

    numbers and source code

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

    The neuron fires strongly on words typical of promotional or legal boilerplate (e.g. “By,” “Minimum,” “many,” “w/,” “count”), so it’s looking for commercial or disclaimer‐style language.

    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
    s
    0.89
    á
    0.75
    '></
    0.74
    పూ
    0.73
    ्स
    0.73
     SignUp
    0.73
     qRT
    0.72
    ارت
    0.72
     pensa
    0.72
     travail
    0.71
    POSITIVE LOGITS
     белән
    0.80
    тың
    0.80
     және
    0.79
     וי
    0.79
     ਅਤੇ
    0.77
    さすが
    0.74
     طويل
    0.74
     ۽
    0.73
     അത
    0.72
    はありません
    0.71
    Activations Density 0.000%

    No Known Activations