© 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. 8168
    Prev
    Next
    INDEX
    Explanations

    docstring or code definition

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

    This neuron flags low‐frequency (i.e. rare or technical) tokens 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
    ม
    1.05
    a
    1.01
    ant
    0.98
    zy
    0.91
    op
    0.90
    llvm
    0.88
    個月
    0.88
    น้ำ
    0.87
    k
    0.87
    ian
    0.85
    POSITIVE LOGITS
     לס
    0.82
     بری
    0.80
     меда
    0.80
     monologue
    0.79
     большин
    0.77
     السؤال
    0.77
    ία
    0.76
     כן
    0.76
     apartness
    0.75
     विषयों
    0.74
    Activations Density 0.000%

    No Known Activations