© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9176
    Prev
    Next
    INDEX
    Explanations

    depending on

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

    The neuron detects words having to do with embedding, linking, or hosting online content (e.g. embed, blogs, server, cloud, Youtube).

    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_31_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
     یعنی
    0.58
     ㅛ
    0.54
     ardından
    0.53
     सारी
    0.53
     schließlich
    0.53
     ili
    0.52
     bütün
    0.52
     좋
    0.52
     或
    0.52
     každý
    0.52
    POSITIVE LOGITS
     etc
    1.07
     എന്നിവ
    1.05
    etc
    1.04
     depending
    1.01
    等が
    0.98
    などが
    0.98
    などの
    0.97
    等的
    0.97
     тощо
    0.97
     প্রভৃতির
    0.96
    Activations Density 0.247%

    No Known Activations